# AssemblyAI Documentation > AssemblyAI provides production-ready Voice AI models for speech-to-text, speaker detection, sentiment analysis, and more. Build with pre-recorded or streaming audio using REST APIs and WebSockets. This is the structured documentation index for AssemblyAI's public API and product documentation. ## Core machine-readable resources - [Full documentation content](https://www.assemblyai.com/docs/llms-full.txt): Complete generated Markdown content for all local docs pages and configured API specs. - [Integration prompt](https://www.assemblyai.com/docs/agent-instructions.md): Rules of the road for AI coding agents building AssemblyAI integrations. - [Documentation index](https://www.assemblyai.com/docs/llms.txt): This file. ## Overview - [AssemblyAI Documentation](https://www.assemblyai.com/docs) (Getting started): Build with our Voice AI Infrastructure - [Build with AI coding agents](https://www.assemblyai.com/docs/coding-agent-prompts) (Getting started): Build with AssemblyAI using Cursor, Claude Code, Copilot, Devin, and other AI coding assistants. Copy the integration prompt, pin the URL in your agent's project instructions, connect the docs MCP server, or install the Claude Code skill. - [Models](https://www.assemblyai.com/docs/getting-started/models) (Getting started): AssemblyAI's speech-to-text models and their capabilities - [Evaluations](https://www.assemblyai.com/docs/evaluations) (Getting started): Figure out which STT models are best for your product with an evaluation. - [Account Management](https://www.assemblyai.com/docs/account-management) (Getting started): Account Management documentation. - [Single Sign-On (SSO)](https://www.assemblyai.com/docs/sso) (Getting started): Set up SAML or OIDC Single Sign-On for your AssemblyAI organization, including step-by-step configuration for Okta, Google Workspace, and Microsoft Entra ID. - [Billing and Pricing](https://www.assemblyai.com/docs/billing-and-pricing) (Getting started): Billing and Pricing documentation. - [Introducing Universal-3.5 Pro](https://www.assemblyai.com/docs/getting-started/universal-3-5-pro) (Getting started): Learn how to transcribe audio using Universal-3.5 Pro. - [End-to-end examples](https://www.assemblyai.com/docs/getting-started/end-to-end-examples) (Getting started > End-to-end examples): Copy-paste pipelines that combine multiple AssemblyAI products in a single script. - [Meeting notetaker](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/meeting-notetaker) (Getting started > End-to-end examples): Transcribe a team meeting with speaker labels, identify speakers by name, then generate structured meeting notes with LLM Gateway. - [Sales call intelligence](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/sales-call-intelligence) (Getting started > End-to-end examples): Transcribe a sales call with speaker labels and sentiment analysis, identify speakers by role, then generate a coaching scorecard with LLM Gateway. - [Medical scribe](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/medical-scribe) (Getting started > End-to-end examples): Transcribe a clinical encounter using Medical Mode with speaker labels and entity detection, then generate a structured SOAP note with LLM Gateway. - [Content repurposing](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/content-repurposing) (Getting started > End-to-end examples): Transcribe a podcast or webinar, extract key phrases, then generate a blog post draft with LLM Gateway. - [Real-time meeting assistant](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/real-time-meeting-assistant) (Getting started > End-to-end examples): Stream audio from your microphone with speaker diarization and LLM Gateway for live transcription and automatic summaries. - [Real-time live captioner](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/real-time-live-captioner) (Getting started > End-to-end examples): Stream audio from your microphone with keyterms prompting for domain-specific accuracy, ideal for live events and accessibility. - [Best Practices for building Meeting Notetakers](https://www.assemblyai.com/docs/meeting-notetaker-best-practices) (Use cases & integrations > Use case guides): Complete guide for building meeting notetakers with AssemblyAI - [Build a medical scribe](https://www.assemblyai.com/docs/medical-scribe-best-practices) (Use cases & integrations > Use case guides > Build a medical scribe): Build AI-powered medical scribes that transcribe patient encounters and generate clinical documentation. - [Build a Post-Visit Medical Scribe](https://www.assemblyai.com/docs/medical-scribe-best-practices/medical-scribe-post-visit) (Use cases & integrations > Use case guides > Build a medical scribe): Complete example implementing pre-recorded transcription with Universal-3 Pro for post-visit clinical documentation. - [Build a Real-Time Medical Scribe](https://www.assemblyai.com/docs/medical-scribe-best-practices/medical-scribe-real-time) (Use cases & integrations > Use case guides > Build a medical scribe): Complete example for real-time streaming medical transcription with LLM Gateway post-processing and SOAP note generation. - [Best Practices for Building Voice Agents](https://www.assemblyai.com/docs/voice-agents/best-practices) (Use cases & integrations > Use case guides): Complete guide for building voice agents with AssemblyAI's Universal-3 Pro Streaming - [Best Practices for building Contact Center Applications](https://www.assemblyai.com/docs/contact-center-best-practices) (Use cases & integrations > Use case guides): Complete guide for building contact center applications with AssemblyAI - [Integrations](https://www.assemblyai.com/docs/integrations) (Use cases & integrations > Integrations): Integrations documentation. - [Universal 3.5 Pro Realtime on LiveKit](https://www.assemblyai.com/docs/voice-agents/livekit-universal-3-5-pro) (Use cases & integrations > Integrations > Voice agent orchestrators): Integrate AssemblyAI's Universal 3.5 Pro Realtime speech-to-text model into a LiveKit voice agent - [Universal 3.5 Pro Realtime on Pipecat](https://www.assemblyai.com/docs/voice-agents/pipecat-universal-3-5-pro) (Use cases & integrations > Integrations > Voice agent orchestrators): Integrate AssemblyAI's Universal 3.5 Pro Realtime speech-to-text model into a Pipecat voice agent - [Zapier Integration with AssemblyAI](https://www.assemblyai.com/docs/integrations/zapier) (Use cases & integrations > Integrations > No-code tools): Transcribe audio in Zapier using the AssemblyAI app. - [Integrate Make with AssemblyAI](https://www.assemblyai.com/docs/integrations/make) (Use cases & integrations > Integrations > No-code tools): Use our Make (formerly Integromat) app to use AssemblyAI's speech AI in your Make scenarios. - [The AssemblyAI n8n Integration](https://www.assemblyai.com/docs/integrations/n-8-n) (Use cases & integrations > Integrations > No-code tools): Integrate AssemblyAI with 1000+ apps and services using n8n's automation platform. - [The Postman collection for the AssemblyAI API](https://www.assemblyai.com/docs/integrations/postman) (Use cases & integrations > Integrations > No-code tools): Use the AssemblyAI API Postman collection to experiment with our API. - [Build a Zoom Real-time transcription bot with Recall.ai](https://www.assemblyai.com/docs/integrations/recall) (Use cases & integrations > Integrations > Meeting transcriber tools): Build a Zoom Real-time transcription bot with Recall.ai documentation. - [Transcribe Your Zoom Meetings](https://www.assemblyai.com/docs/integrations/zoom-rtms) (Use cases & integrations > Integrations > Meeting transcriber tools): Transcribe Your Zoom Meetings documentation. - [Integrate Telnyx with AssemblyAI](https://www.assemblyai.com/docs/integrations/telnyx) (Use cases & integrations > Integrations > Telephony tools): Build voice agents with Telnyx and AssemblyAI using Pipecat or LiveKit. - [Integrate Twilio with AssemblyAI](https://www.assemblyai.com/docs/integrations/twilio) (Use cases & integrations > Integrations > Telephony tools): Transcribe Twilio Voice data using AssemblyAI. - [Transcribe Your Amazon Connect Recordings](https://www.assemblyai.com/docs/integrations/amazon-connect) (Use cases & integrations > Integrations > Telephony tools): Transcribe Your Amazon Connect Recordings documentation. - [Transcribe Genesys Cloud Recordings with AssemblyAI](https://www.assemblyai.com/docs/integrations/genesys-cloud) (Use cases & integrations > Integrations > Telephony tools): Transcribe Genesys Cloud Recordings with AssemblyAI documentation. - [\U0001F99C️\U0001F517 LangChain Integration with AssemblyAI](https://www.assemblyai.com/docs/integrations/langchain) (Use cases & integrations > Integrations > Community-maintained tools > LangChain): Transcribe audio in LangChain using the built-in integration with AssemblyAI. - [\U0001F99C️\U0001F517 LangChain Python Integration with AssemblyAI](https://www.assemblyai.com/docs/integrations/langchain/python) (Use cases & integrations > Integrations > Community-maintained tools > LangChain): Transcribe audio in LangChain Python using the built-in integration with AssemblyAI. - [\U0001F99C️\U0001F517 LangChain JavaScript Integration with AssemblyAI](https://www.assemblyai.com/docs/integrations/langchain/js) (Use cases & integrations > Integrations > Community-maintained tools > LangChain): Transcribe audio in LangChain.JS using the built-in integration with AssemblyAI. - [▲ Vercel AI SDK Integration with AssemblyAI](https://www.assemblyai.com/docs/integrations/vercel-ai-sdk) (Use cases & integrations > Integrations > Community-maintained tools): Transcribe audio with the Vercel AI SDK using the official @ai-sdk/assemblyai provider. - [Integrate Power Automate with AssemblyAI](https://www.assemblyai.com/docs/integrations/power-automate) (Use cases & integrations > Integrations > Community-maintained tools): Use our Power Automate & Azure Logic Apps connector to use AssemblyAI's speech AI in your flows. - [Semantic Kernel Integration for AssemblyAI](https://www.assemblyai.com/docs/integrations/semantic-kernel) (Use cases & integrations > Integrations > Community-maintained tools): Transcribe audio in Semantic Kernel for C# .NET using the built-in integration with AssemblyAI. - [Integrate Activepieces with AssemblyAI](https://www.assemblyai.com/docs/integrations/activepieces) (Use cases & integrations > Integrations > Community-maintained tools): Add Speech AI to your Activepieces flows with the AssemblyAI piece. - [Haystack Integration for AssemblyAI](https://www.assemblyai.com/docs/integrations/haystack) (Use cases & integrations > Integrations > Community-maintained tools): Transcribe, summarize and diarize audio in a Haystack pipeline with Python using the integration with AssemblyAI. - [Cloudflare](https://www.assemblyai.com/docs/nav-links/cloudflare) (Use cases & integrations > Integrations > Community-maintained tools): Open Cloudflare. - [Relay.app](https://www.assemblyai.com/docs/nav-links/relay-app) (Use cases & integrations > Integrations > Community-maintained tools): Open Relay.app. - [Bubble by Knowcode](https://www.assemblyai.com/docs/nav-links/bubble-by-knowcode) (Use cases & integrations > Integrations > Community-maintained tools): Open Bubble by Knowcode. - [Pipedream](https://www.assemblyai.com/docs/nav-links/pipedream) (Use cases & integrations > Integrations > Community-maintained tools): Open Pipedream. - [Drupal](https://www.assemblyai.com/docs/nav-links/drupal) (Use cases & integrations > Integrations > Community-maintained tools): Open Drupal. - [Trust center](https://www.assemblyai.com/docs/nav-links/trust-center) (Trust & security): Open Trust center. - [Security overview](https://www.assemblyai.com/docs/nav-links/security-overview) (Trust & security): Open Security overview. - [Data Controls](https://www.assemblyai.com/docs/data-controls) (Trust & security): Manage how AssemblyAI retains and uses your data — opt out of the model improvement program, set a time-to-live for audio and transcripts, and sign a BAA, all self-serve from the dashboard. - [Data retention and model training](https://www.assemblyai.com/docs/data-retention-and-model-training) (Trust & security): Learn about how AssemblyAI handles data retention, encryption, model training, and compliance. ## API Reference - [API Reference](https://www.assemblyai.com/docs/api-reference/overview) (Overview): Choose an API to view its full reference. ## Pre-recorded STT - [Quickstart](https://www.assemblyai.com/docs/pre-recorded-audio/getting-started/transcribe-an-audio-file) (Getting started): Learn how to transcribe and analyze an audio file. - [Model selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model) (Getting started): Model selection documentation. - [Prompting and Keyterms](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-5-pro/prompting) (Features): Prompting and Keyterms documentation. - [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode) (Features): Improve transcription accuracy for medical terminology in pre-recorded audio - [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers) (Features): Add speaker labels to your transcript - [Multichannel Transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels) (Features): Multichannel Transcription documentation. - [Code Switching](https://www.assemblyai.com/docs/pre-recorded-audio/code-switching) (Features): Code Switching documentation. - [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection) (Features > Languages): Detect the dominant language and automatically route your request to the best available speech model for that language. - [Set Language Manually](https://www.assemblyai.com/docs/pre-recorded-audio/set-language-manually) (Features > Languages): Specify a dominant language via language_code to route your request to the best available speech model for that language. - [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages) (Features > Languages): Supported languages for pre-recorded audio speech-to-text models. - [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms) (Features): Custom Spelling documentation. - [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words) (Features): Filler Words documentation. - [Word Search](https://www.assemblyai.com/docs/pre-recorded-audio/search-for-words-in-transcript) (Features): Word Search documentation. - [Set the Start and End of the Transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript) (Features): Set the Start and End of the Transcript documentation. - [Transcript Status](https://www.assemblyai.com/docs/pre-recorded-audio/check-transcript-status) (Features > Transcription operations): Transcript Status documentation. - [Transcript export options](https://www.assemblyai.com/docs/pre-recorded-audio/export-transcripts-as-srt-vtt-or-text) (Features > Transcription operations): Transcript export options documentation. - [Delete Transcripts](https://www.assemblyai.com/docs/pre-recorded-audio/delete-transcripts) (Features > Transcription operations): Delete Transcripts documentation. - [Upload a media file](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/files/upload) (API reference): Upload a media file to AssemblyAI. - [Submit a transcript](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/submit) (API reference): Create a transcription request. - [Get a transcript](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get) (API reference): Retrieve a transcript by ID. - [Get transcript sentences](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get-sentences) (API reference): Retrieve transcript sentences. - [Get transcript paragraphs](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get-paragraphs) (API reference): Retrieve transcript paragraphs. - [Get subtitles](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get-subtitles) (API reference): Export subtitles for a transcript. - [Get redacted audio](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get-redacted-audio) (API reference): Retrieve redacted audio for a transcript. - [Word search](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/word-search) (API reference): Search a transcript for words or phrases. - [List transcripts](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/list) (API reference): List transcripts. - [Delete a transcript](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/delete) (API reference): Delete a transcript. - [Webhooks for pre-recorded audio](https://www.assemblyai.com/docs/pre-recorded-audio/webhooks) (Advanced): Get notified when a pre-recorded audio transcription is ready. - [Benchmarks](https://www.assemblyai.com/docs/pre-recorded-audio/benchmarks) (Advanced): Industry-leading accuracy for pre-recorded speech-to-text. - [Evaluating Pre-recorded STT models](https://www.assemblyai.com/docs/pre-recorded-audio/evaluations) (Advanced): Evaluating Pre-recorded STT models documentation. - [Cloud Endpoints and Data Residency](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-region) (Advanced): Cloud Endpoints and Data Residency documentation. - [Rate limits](https://www.assemblyai.com/docs/pre-recorded-audio/rate-limits) (Advanced): Rate limits documentation. - [Migration guide: Deepgram to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/dg_to_aai) (Guides > Migration guides): Migration guide: Deepgram to AssemblyAI documentation. - [Migration guide: OpenAI to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/oai_to_aai) (Guides > Migration guides): Migration guide: OpenAI to AssemblyAI documentation. - [Migration guide: AWS Transcribe to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/aws_to_aai) (Guides > Migration guides): Migration guide: AWS Transcribe to AssemblyAI documentation. - [Migration guide: Google Speech-to-Text to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/google_to_aai) (Guides > Migration guides): Migration guide: Google Speech-to-Text to AssemblyAI documentation. - [Migration guide: Gladia to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/gladia_to_aai) (Guides > Migration guides): Migration guide: Gladia to AssemblyAI documentation. - [Best Practices for building Meeting Notetakers](https://www.assemblyai.com/docs/meeting-notetaker-best-practices) (Guides > Tutorials): Complete guide for building meeting notetakers with AssemblyAI - [Build a medical scribe](https://www.assemblyai.com/docs/medical-scribe-best-practices) (Guides > Tutorials): Build AI-powered medical scribes that transcribe patient encounters and generate clinical documentation. - [Best Practices for building Contact Center Applications](https://www.assemblyai.com/docs/contact-center-best-practices) (Guides > Tutorials): Complete guide for building contact center applications with AssemblyAI - [Get YouTube Video Transcripts with yt-dlp](https://www.assemblyai.com/docs/pre-recorded-audio/guides/transcribe_youtube_videos) (Guides > Tutorials > Basic transcription workflows): Get YouTube Video Transcripts with yt-dlp documentation. - [Build a UI for Transcription with Gradio and Python](https://www.assemblyai.com/docs/pre-recorded-audio/guides/gradio-frontend) (Guides > Tutorials > Basic transcription workflows): Build a UI for Transcription with Gradio and Python documentation. - [Detect Low Confidence Words in a Transcript](https://www.assemblyai.com/docs/pre-recorded-audio/guides/detecting-low-confidence-words) (Guides > Tutorials > Basic transcription workflows): Detect Low Confidence Words in a Transcript documentation. - [Running Bulk Transcription and Load Tests at Scale](https://www.assemblyai.com/docs/pre-recorded-audio/guides/bulk-transcription-and-load-tests-at-scale) (Guides > Tutorials > Batch transcription): Best practices for submitting large volumes of audio files for transcription, including one-off load tests. - [Transcribe Multiple Files Simultaneously Using the JavaScript SDK](https://www.assemblyai.com/docs/pre-recorded-audio/guides/sdk-node-batch) (Guides > Tutorials > Batch transcription): Transcribe Multiple Files Simultaneously Using the JavaScript SDK documentation. - [Transcribe Multiple Files Simultaneously Using the Python SDK](https://www.assemblyai.com/docs/pre-recorded-audio/guides/batch_transcription) (Guides > Tutorials > Batch transcription): Transcribe Multiple Files Simultaneously Using the Python SDK documentation. - [Transcribe from an S3 Bucket](https://www.assemblyai.com/docs/pre-recorded-audio/guides/transcribe_from_s3) (Guides > Tutorials > Hosting audio files): Transcribe from an S3 Bucket documentation. - [Transcribe Google Drive Files](https://www.assemblyai.com/docs/pre-recorded-audio/guides/transcribing-google-drive-file) (Guides > Tutorials > Hosting audio files): Transcribe Google Drive Files documentation. - [Transcribe GitHub Files](https://www.assemblyai.com/docs/pre-recorded-audio/guides/transcribing-github-files) (Guides > Tutorials > Hosting audio files): Transcribe GitHub Files documentation. - [Iterate over Speaker Labels with Make.com](https://www.assemblyai.com/docs/pre-recorded-audio/guides/make-speaker-labels) (Guides > Tutorials > Speaker labels): Iterate over Speaker Labels with Make.com documentation. - [Calculate the Talk / Listen Ratio of Speakers](https://www.assemblyai.com/docs/pre-recorded-audio/guides/talk-listen-ratio) (Guides > Tutorials > Speaker labels): Calculate the Talk / Listen Ratio of Speakers documentation. - [Plot A Speaker Timeline with Matplotlib](https://www.assemblyai.com/docs/pre-recorded-audio/guides/speaker_timeline) (Guides > Tutorials > Speaker labels): Plot A Speaker Timeline with Matplotlib documentation. - [Generate Custom Speaker Labels with Pyannote](https://www.assemblyai.com/docs/pre-recorded-audio/guides/Use_AssemblyAI_with_Pyannote_to_generate_custom_Speaker_Labels) (Guides > Tutorials > Speaker labels): Generate Custom Speaker Labels with Pyannote documentation. - [Use Speaker Diarization with Async Chunking](https://www.assemblyai.com/docs/pre-recorded-audio/guides/speaker-diarization-with-async-chunking) (Guides > Tutorials > Speaker labels): Use Speaker Diarization with Async Chunking documentation. - [Setup A Speaker Identification System using Pinecone & Nvidia TitaNet](https://www.assemblyai.com/docs/pre-recorded-audio/guides/titanet-speaker-identification) (Guides > Tutorials > Speaker labels): Setup A Speaker Identification System using Pinecone & Nvidia TitaNet documentation. - [Use Automatic Language Detection as a Separate Step From Transcription](https://www.assemblyai.com/docs/pre-recorded-audio/guides/automatic-language-detection-separate) (Guides > Tutorials > Automatic Language Detection): Use Automatic Language Detection as a Separate Step From Transcription documentation. - [Route to Default Language if Language Confidence is Low](https://www.assemblyai.com/docs/pre-recorded-audio/guides/automatic-language-detection-route-default-language) (Guides > Tutorials > Automatic Language Detection): Route to Default Language if Language Confidence is Low documentation. - [Create Custom Length Subtitles](https://www.assemblyai.com/docs/pre-recorded-audio/guides/subtitle_creation_by_word_count) (Guides > Tutorials > Subtitles): Create Custom Length Subtitles documentation. - [Create Subtitles with Speaker Labels](https://www.assemblyai.com/docs/pre-recorded-audio/guides/speaker_labelled_subtitles) (Guides > Tutorials > Subtitles): Create Subtitles with Speaker Labels documentation. - [Generate Subtitles for Videos](https://www.assemblyai.com/docs/pre-recorded-audio/guides/subtitles) (Guides > Tutorials > Subtitles): Generate Subtitles for Videos documentation. - [Translate an AssemblyAI Subtitle Transcript](https://www.assemblyai.com/docs/pre-recorded-audio/guides/translate_subtitles) (Guides > Tutorials > Subtitles): Translate an AssemblyAI Subtitle Transcript documentation. - [Schedule a DELETE request with AssemblyAI and EasyCron](https://www.assemblyai.com/docs/pre-recorded-audio/guides/schedule_delete) (Guides > Tutorials > Delete transcripts): Schedule a DELETE request with AssemblyAI and EasyCron documentation. - [Troubleshoot Common Errors](https://www.assemblyai.com/docs/pre-recorded-audio/guides/common_errors_and_solutions) (Guides > Tutorials > Error handling and audio file fixes): Troubleshoot Common Errors documentation. - [Implement Retry Server Error Logic](https://www.assemblyai.com/docs/pre-recorded-audio/guides/retry-server-error) (Guides > Tutorials > Error handling and audio file fixes): Implement Retry Server Error Logic documentation. - [Implement Retry Upload Error Logic](https://www.assemblyai.com/docs/pre-recorded-audio/guides/retry-upload-error) (Guides > Tutorials > Error handling and audio file fixes): Implement Retry Upload Error Logic documentation. - [Identify Duplicate Dual Channel Files](https://www.assemblyai.com/docs/pre-recorded-audio/guides/identify_duplicate_channels) (Guides > Tutorials > Error handling and audio file fixes): Identify Duplicate Dual Channel Files documentation. - [Correct Audio Duration Discrepancies with Multi-Tool Validation and Transcoding](https://www.assemblyai.com/docs/pre-recorded-audio/guides/audio-duration-fix) (Guides > Tutorials > Error handling and audio file fixes): Correct Audio Duration Discrepancies with Multi-Tool Validation and Transcoding documentation. - [Audio File Downsampling Recommendations and Best Practices](https://www.assemblyai.com/docs/pre-recorded-audio/guides/downsampling) (Guides > Tutorials > Error handling and audio file fixes): Learn best practices for reducing audio file size while maintaining transcription quality with AssemblyAI - [Translate an AssemblyAI Subtitle Transcript](https://www.assemblyai.com/docs/pre-recorded-audio/guides/translate_subtitles) (Guides > Tutorials > Translation): Translate an AssemblyAI Subtitle Transcript documentation. - [Translate AssemblyAI Transcripts Into Other Languages Using Commercial Models](https://www.assemblyai.com/docs/pre-recorded-audio/guides/translate_transcripts) (Guides > Tutorials > Translation): Translate AssemblyAI Transcripts Into Other Languages Using Commercial Models documentation. - [Transform Chinese transcripts into Simplified or Traditional Text](https://www.assemblyai.com/docs/pre-recorded-audio/guides/traditional_simplified_chinese) (Guides > Tutorials > Translation): Transform Chinese transcripts into Simplified or Traditional Text documentation. - [Do More With Our SDKs](https://www.assemblyai.com/docs/pre-recorded-audio/guides/do-more-with-sdk) (Guides > Tutorials > Do more with our SDKs): Do More With Our SDKs documentation. ## Real-time STT - [Quickstart](https://www.assemblyai.com/docs/streaming/getting-started/transcribe-streaming-audio) (Getting started): Learn how to transcribe streaming audio. - [Model selection](https://www.assemblyai.com/docs/streaming/select-the-speech-model) (Getting started): Model selection documentation. - [Optimizing Accuracy and Latency](https://www.assemblyai.com/docs/streaming/getting-started/optimizing-accuracy-and-latency) (Getting started): Tune streaming models to balance transcription accuracy and latency. - [Turn Detection](https://www.assemblyai.com/docs/streaming/turn-detection) (Features): Turn Detection documentation. - [Prompting and Keyterms](https://www.assemblyai.com/docs/streaming/prompting-and-keyterms) (Features): Prompting and Keyterms documentation. - [Conversation Context](https://www.assemblyai.com/docs/streaming/universal-3-5-pro/context-carryover) (Features): Conversation Context documentation. - [Multilingual Transcription](https://www.assemblyai.com/docs/streaming/multilingual-transcription) (Features): Multilingual Transcription documentation. - [Medical Mode](https://www.assemblyai.com/docs/streaming/medical-mode) (Features): Medical Mode documentation. - [Voice Focus](https://www.assemblyai.com/docs/streaming/voice-focus) (Features): Voice Focus documentation. - [Streaming Diarization and Multichannel](https://www.assemblyai.com/docs/streaming/label-speakers-and-separate-channels) (Features): Streaming Diarization and Multichannel documentation. - [PII Redaction](https://www.assemblyai.com/docs/streaming/pii-redaction) (Features): PII Redaction documentation. - [Filter profanity](https://www.assemblyai.com/docs/streaming/filter-profanity-from-transcripts) (Features): Filter profanity documentation. - [Message Sequence](https://www.assemblyai.com/docs/streaming/message-sequence) (API reference): Canonical reference for the streaming WebSocket protocol. Covers every client and server message and the order they appear in. - [Streaming WebSocket API](https://www.assemblyai.com/docs/streaming/api-spec/streaming-websocket) (API reference): Full AsyncAPI reference for the Real-time STT WebSocket API. - [Generate streaming token](https://www.assemblyai.com/docs/streaming/api-spec/generate-streaming-token) (API reference): Generate a temporary token for Real-time STT. - [Authenticate with a temporary token](https://www.assemblyai.com/docs/streaming/authenticate-with-a-temporary-token) (Advanced): Authenticate with a temporary token documentation. - [Webhooks for streaming speech-to-text](https://www.assemblyai.com/docs/streaming/webhooks) (Advanced): Get notified when a streaming transcription session ends. - [Updating Configuration Mid-Stream](https://www.assemblyai.com/docs/streaming/updating-configuration-mid-stream) (Advanced): Update streaming session parameters without reconnecting using the UpdateConfiguration message. - [Common session errors and closures](https://www.assemblyai.com/docs/streaming/common-session-errors-and-closures) (Advanced): Common session errors and closures documentation. - [Benchmarks](https://www.assemblyai.com/docs/streaming/benchmarks) (Advanced): Industry-leading accuracy for streaming speech-to-text. - [Evaluating Real-time STT models for Voice Agents](https://www.assemblyai.com/docs/streaming/evaluations/voice-agents) (Advanced): Evaluating Real-time STT models for Voice Agents documentation. - [Streaming Endpoints and Data Zones](https://www.assemblyai.com/docs/streaming/endpoints-and-data-zones) (Advanced): Streaming Endpoints and Data Zones documentation. - [Rate limits](https://www.assemblyai.com/docs/streaming/rate-limits) (Advanced): Rate limits documentation. - [Self-Hosted Streaming](https://www.assemblyai.com/docs/streaming/self-hosted-streaming) (Advanced): Deploy AssemblyAI's streaming transcription solution within your own infrastructure - [Universal 3.5 Pro Realtime on LiveKit](https://www.assemblyai.com/docs/voice-agents/livekit-universal-3-5-pro) (Integrations): Integrate AssemblyAI's Universal 3.5 Pro Realtime speech-to-text model into a LiveKit voice agent - [Universal 3.5 Pro Realtime on Pipecat](https://www.assemblyai.com/docs/voice-agents/pipecat-universal-3-5-pro) (Integrations): Integrate AssemblyAI's Universal 3.5 Pro Realtime speech-to-text model into a Pipecat voice agent - [Streaming Migration Guide: Universal Streaming to Universal-3.5 Pro Streaming](https://www.assemblyai.com/docs/streaming/migration-guides/universal-to-universal-3-5-pro-streaming) (Guides > Migration guides): Streaming Migration Guide: Universal Streaming to Universal-3.5 Pro Streaming documentation. - [Streaming Migration Guide: Deepgram to AssemblyAI](https://www.assemblyai.com/docs/streaming/migration-guides/dg_to_aai_streaming) (Guides > Migration guides): Streaming Migration Guide: Deepgram to AssemblyAI documentation. - [Migration guide: Speechmatics to AssemblyAI](https://www.assemblyai.com/docs/streaming/migration-guides/speechmatics_to_aai_streaming) (Guides > Migration guides): Migration guide: Speechmatics to AssemblyAI documentation. - [Streaming Migration Guide: Gladia to AssemblyAI](https://www.assemblyai.com/docs/streaming/migration-guides/gladia-to-aai-streaming) (Guides > Migration guides): Streaming Migration Guide: Gladia to AssemblyAI documentation. - [Best Practices for building Meeting Notetakers](https://www.assemblyai.com/docs/meeting-notetaker-best-practices) (Guides > Tutorials): Complete guide for building meeting notetakers with AssemblyAI - [Build a medical scribe](https://www.assemblyai.com/docs/medical-scribe-best-practices) (Guides > Tutorials): Build AI-powered medical scribes that transcribe patient encounters and generate clinical documentation. - [Best Practices for Building Voice Agents](https://www.assemblyai.com/docs/voice-agents/best-practices) (Guides > Tutorials): Complete guide for building voice agents with AssemblyAI's Universal-3 Pro Streaming - [Best Practices for building Contact Center Applications](https://www.assemblyai.com/docs/contact-center-best-practices) (Guides > Tutorials): Complete guide for building contact center applications with AssemblyAI - [Stream a pre-recorded file in real time](https://www.assemblyai.com/docs/streaming/guides/stream_prerecorded_file_realtime) (Guides > Tutorials > Basic streaming workflows): Stream a pre-recorded file in real time documentation. - [Transcribe System Audio in Real-Time (macOS)](https://www.assemblyai.com/docs/streaming/guides/transcribe_system_audio) (Guides > Tutorials > Basic streaming workflows): Transcribe System Audio in Real-Time (macOS) documentation. - [Terminate Streaming Session After Inactivity](https://www.assemblyai.com/docs/streaming/guides/terminate_realtime_programmatically) (Guides > Tutorials > Basic streaming workflows): Terminate Streaming Session After Inactivity documentation. - [Migrating from Streaming v2 to Streaming v3 (Python)](https://www.assemblyai.com/docs/streaming/guides/v2_to_v3_migration) (Guides > Tutorials > Basic streaming workflows): Migrating from Streaming v2 to Streaming v3 (Python) documentation. - [Migrating from Streaming v2 to Streaming v3 (JavaScript)](https://www.assemblyai.com/docs/streaming/guides/v2_to_v3_migration_js) (Guides > Tutorials > Basic streaming workflows): Migrating from Streaming v2 to Streaming v3 (JavaScript) documentation. - [Next.js example using Real-time STT](https://www.assemblyai.com/docs/nav-links/next-js-example-using-streaming-stt) (Guides > Tutorials > Streaming for front-end applications): Open Next.js example using Real-time STT. - [Vanilla Javascript example using Real-time STT](https://www.assemblyai.com/docs/nav-links/vanilla-javascript-example-using-streaming-stt) (Guides > Tutorials > Streaming for front-end applications): Open Vanilla Javascript example using Real-time STT. - [Apply LLM Gateway to Streaming](https://www.assemblyai.com/docs/streaming/guides/real_time_llm_gateway) (Guides > Tutorials > Streaming with LLM Gateway): Learn how to analyze streaming audio transcripts using LLM Gateway. - [Translate Real-time STT Transcripts with LLM Gateway](https://www.assemblyai.com/docs/streaming/guides/real_time_translation) (Guides > Tutorials > Streaming with LLM Gateway): Translate Real-time STT Transcripts with LLM Gateway documentation. - [Apply Noise Reduction to Audio for Streaming Speech-to-Text](https://www.assemblyai.com/docs/streaming/guides/noise_reduction_streaming) (Guides > Tutorials > Use-case specific streaming workflows): Apply Noise Reduction to Audio for Streaming Speech-to-Text documentation. - [Transcribe audio files with Streaming](https://www.assemblyai.com/docs/streaming/guides/streaming_transcribe_audio_file) (Guides > Tutorials > Use-case specific streaming workflows): Transcribe audio files with Streaming documentation. - [Evaluate Streaming transcription accuracy with WER](https://www.assemblyai.com/docs/streaming/guides/evaluate_streaming_wer) (Guides > Tutorials > Use-case specific streaming workflows): Evaluate Streaming transcription accuracy with WER documentation. - [Determine Optimal Turn Detection Settings from Historical Audio Analysis](https://www.assemblyai.com/docs/streaming/guides/turn_detection_improvement_using_async) (Guides > Tutorials > Use-case specific streaming workflows): Determine Optimal Turn Detection Settings from Historical Audio Analysis documentation. ## Sync STT - [Transcribe a short audio file](https://www.assemblyai.com/docs/sync-stt/getting-started/transcribe-a-short-audio-file) (Getting started): Learn how to transcribe an audio file synchronously with the Sync API. - [Prompting and Keyterms](https://www.assemblyai.com/docs/sync-stt/prompting-and-keyterms) (Features): Prompting and Keyterms documentation. - [Conversation context](https://www.assemblyai.com/docs/sync-stt/conversation-context) (Features): Improve multi-turn transcription accuracy by passing prior dialogue with each request. - [Language selection](https://www.assemblyai.com/docs/sync-stt/language-selection) (Features): Steer Sync STT transcription toward one or more languages with the language_code field. - [Word timestamps](https://www.assemblyai.com/docs/sync-stt/word-timestamps) (Features): Get exact per-word start and end times with your synchronous transcript. - [Transcribe a short audio file](https://www.assemblyai.com/docs/api-reference/sync-api/transcribe) (API reference): Synchronously transcribe an audio file up to 120 seconds. - [Pre-warm a connection](https://www.assemblyai.com/docs/api-reference/sync-api/warm) (API reference): Establish the HTTPS connection ahead of a /transcribe request to take the TLS handshake off the critical path. - [Audio requirements](https://www.assemblyai.com/docs/sync-stt/audio-requirements) (Advanced): Duration, size, format, and sample-rate constraints for Sync STT audio. - [Error handling](https://www.assemblyai.com/docs/sync-stt/error-handling) (Advanced): Sync STT error responses, status codes, and retry guidance. - [Cloud endpoints & data residency](https://www.assemblyai.com/docs/sync-stt/endpoints-and-data-zones) (Advanced): AssemblyAI Sync STT endpoints for global routing and US/EU data residency. - [Connection pre-warming](https://www.assemblyai.com/docs/sync-stt/connection-pre-warming) (Advanced): Use the /warm endpoint to take the TLS handshake off the critical path of a synchronous transcription request. ## Voice Agent API - [Voice Agent API](https://www.assemblyai.com/docs/voice-agents/voice-agent-api) (Getting started): Real-time voice agents that talk and listen. Configure an agent once, then deploy it to a browser, your own app, or the phone. - [Build with AI coding tools](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/build-with-ai-tools) (Getting started): Point your AI coding assistant at AssemblyAI's live docs so it writes correct, current Voice Agent code instead of guessing from stale training data. - [Supported languages](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/supported-languages) (Getting started): Input and output languages supported by the Voice Agent API. - [Create an agent](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/create-agent) (Create & manage agents): Create a reusable voice agent with a single REST call. - [Manage agents](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/manage-agents) (Create & manage agents): REST reference for creating and managing reusable voice agents. Endpoints, request and response schemas, the HTTP tool schema, and validation rules. - [Create an agent](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/create-agent) (Create & manage agents > Endpoints): Create a reusable voice agent. - [List agents](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/list-agents) (Create & manage agents > Endpoints): List all voice agents in your account. - [Retrieve an agent](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/get-agent) (Create & manage agents > Endpoints): Retrieve a stored voice agent by ID. - [Update an agent](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/update-agent) (Create & manage agents > Endpoints): Update the configuration of a stored voice agent. - [Delete an agent](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/delete-agent) (Create & manage agents > Endpoints): Delete a stored voice agent. - [Connect your own LLM](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/connect-your-own-llm) (Agent behavior): Point a voice agent at your own OpenAI-compatible LLM endpoint instead of AssemblyAI's managed model. - [Prompting guide](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/prompting-guide) (Agent behavior): Patterns for writing system prompts that improve instruction following, conversationality, and voice output quality. - [Greeting](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/greeting) (Agent behavior): Set the exact words a voice agent speaks when a conversation starts, or omit it to listen first. - [Tools](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/tools/overview) (Agent behavior > Tools): Give your agent tools to fetch data and take actions, plus the parameter hints, execution modes, and patterns that make tool calls and turn-taking reliable. - [HTTP tools](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/tools/http-tools) (Agent behavior > Tools): Server-side tools. Give your agent a URL and a parameter list, and AssemblyAI makes the request for you when the model calls the tool. - [Client-side tools](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/tools/client-side-tools) (Agent behavior > Tools): Function tools your own code runs. Declare them inline, handle the tool.call, and return a tool.result without breaking turn-taking. - [Voices](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/voices) (Conversational experience): Pick a voice that matches your agent's personality and language. - [Output volume](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/volume) (Conversational experience): Set how loud a voice agent's speech plays back. - [Turn detection and interruptions](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/turn-detection-and-interruptions) (Conversational experience): How the Voice Agent API decides when the user has finished speaking and when they're interrupting. On by default, no tuning required. - [Add transcription context](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/transcription-prompt) (Conversational experience): Improve a voice agent's transcription accuracy for domain terms with a contextual prompt and a key terms list. - [Steer toward known languages](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/language-selection) (Conversational experience): Steer a voice agent's speech-to-text toward the languages you expect with language_codes, or leave it on automatic multilingual detection. - [Isolate the caller's voice](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/noise-suppression) (Conversational experience): Isolate the caller's voice and suppress background noise before it reaches the agent's speech-to-text, with voice_focus. - [Deploy your agent](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/deploy) (Deploy): Deploy your agent documentation. - [Browser integration](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/browser-integration) (Deploy): Connect browser-based apps to the Voice Agent API using a temporary token. - [Set up an inbound phone agent via SIP](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/connect-to-twilio) (Deploy): Point a Twilio number you already own at AssemblyAI over a SIP trunk and attach a voice agent. Inbound only. - [Audio format](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/audio-format) (Deploy): Audio format documentation. - [Recordings & transcripts](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/session-history) (After a session): List voice agent sessions and retrieve each one's recording, conversation timeline, and metadata, with examples for parsing transcripts and playing back audio. - [List sessions](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/list-sessions) (After a session > Endpoints): List your voice agent sessions, newest first. - [Retrieve a session](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/get-session) (After a session > Endpoints): Retrieve a voice agent session by ID, including its recording, timeline, and metadata artifacts. - [Delete a session](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/delete-session) (After a session > Endpoints): Soft-delete a voice agent session. - [Inline session configuration](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/session-configuration) (Reference): Configure a voice agent at connect-time over the WebSocket with session.update, without storing an agent. - [Events reference](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/events-reference) (Reference): Every client-to-server and server-to-client event for the Voice Agent API. - [Troubleshooting](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/troubleshooting) (Reference): Common issues and fixes when building with the Voice Agent API. - [Message Sequence](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/message-sequence) (API reference): Canonical reference for the Voice Agent WebSocket protocol. Covers every client and server event and the order they appear in. - [Voice Agent WebSocket API](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/voice-agent-websocket) (API reference): Full AsyncAPI reference for the Voice Agent WebSocket. - [Generate voice agent token](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/generate-voice-agent-token) (API reference): Generate a temporary token for the Voice Agent API. ## Speech Understanding - [Speech Understanding](https://www.assemblyai.com/docs/speech-understanding/getting-started) (Models & features): Extract structured insights from audio with Speech Understanding models. - [Action Items](https://www.assemblyai.com/docs/speech-understanding/action-items) (Models & features): Generate action items of your audio transcripts - [Rate limits](https://www.assemblyai.com/docs/speech-understanding/rate-limits) (Models & features): Rate limits documentation. - [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters) (Models & features): Automatically segment your audio into chapters with summaries using LLM Gateway - [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting) (Models & features): Automatically format dates, phone numbers, emails, and more in your transcripts - [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection) (Models & features): Extract named entities from your audio file - [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases) (Models & features): Label key phrases that are spoken in your audio - [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis) (Models & features): Detect the sentiment of speech in your audio - [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification) (Models & features): Identify speakers by name or role in your transcript - [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization) (Models & features): Generate summaries of your audio transcripts - [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection) (Models & features): Label topics that are mentioned in your audio file - [Translation](https://www.assemblyai.com/docs/speech-understanding/translation) (Models & features): Translate your transcripts from one language to another - [Migration guide: Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/migration-guides/auto-chapters) (Guides > Migration guides): Migration guide: Auto Chapters documentation. - [Migration guide: Summarization](https://www.assemblyai.com/docs/speech-understanding/migration-guides/summarization) (Guides > Migration guides): Migration guide: Summarization documentation. ## Guardrails - [Guardrails](https://www.assemblyai.com/docs/guardrails/getting-started) (Models & features): Protect sensitive content in your transcripts with guardrail features. - [PII Redaction](https://www.assemblyai.com/docs/guardrails/redact-pii-from-transcripts) (Models & features): Redact PII that is spoken in your audio - [Content Moderation](https://www.assemblyai.com/docs/guardrails/detect-sensitive-content) (Models & features): Detect sensitive content in your audio files - [Profanity Filtering](https://www.assemblyai.com/docs/guardrails/filter-profanity-from-transcripts) (Models & features): Profanity Filtering documentation. - [Speech Threshold](https://www.assemblyai.com/docs/guardrails/set-minimum-speech-threshold) (Models & features): Speech Threshold documentation. ## LLM Gateway - [Quickstart](https://www.assemblyai.com/docs/llm-gateway/quickstart) (Getting started): AssemblyAI's LLM Gateway is a unified API providing access to 25+ models from Claude, GPT, Gemini, and more through a single interface. - [Models](https://www.assemblyai.com/docs/llm-gateway/available-models) (Getting started): Available models on LLM Gateway - [Providers](https://www.assemblyai.com/docs/llm-gateway/providers) (Getting started): Model providers available through LLM Gateway, including data retention policies and regional availability - [Model Fallbacks](https://www.assemblyai.com/docs/llm-gateway/fallback) (Features): Automatically fall back to an alternative LLM model when your primary model fails - [Prompt Caching](https://www.assemblyai.com/docs/llm-gateway/prompt-caching) (Features): Reduce latency and costs by caching repeated prompt content across LLM Gateway requests - [Tool Calling](https://www.assemblyai.com/docs/llm-gateway/tool-calling) (Features): Enable models to execute custom functions to access external data or functionality - [Structured Outputs](https://www.assemblyai.com/docs/llm-gateway/structured-outputs) (Features): Constrain model responses to follow a specific JSON schema for reliable, parseable outputs - [Cloud Endpoints and Data Residency](https://www.assemblyai.com/docs/llm-gateway/cloud-endpoints-and-data-residency) (Features): Choose LLM Gateway endpoints for data residency requirements. - [Create a chat completion](https://www.assemblyai.com/docs/llm-gateway/api-reference/create-chat-completion) (API reference): Create a chat completion with LLM Gateway. - [Create speech understanding](https://www.assemblyai.com/docs/llm-gateway/api-reference/create-speech-understanding) (API reference): Apply LLM Gateway to audio transcripts. - [List available models](https://www.assemblyai.com/docs/llm-gateway/api-reference/list-available-models) (API reference): List the models available through LLM Gateway. - [Improve Latency](https://www.assemblyai.com/docs/llm-gateway/improve-latency) (Core concepts): Use keep-alive connections to minimize latency - [Ask Questions About Your Audio Transcripts](https://www.assemblyai.com/docs/llm-gateway/ask-questions) (Core concepts): Ask questions about your audio transcripts using LLM Gateway. - [Agentic Workflows](https://www.assemblyai.com/docs/llm-gateway/agentic-workflows) (Core concepts): Build multi-step reasoning applications with automatic tool chaining - [Basic Chat Completions](https://www.assemblyai.com/docs/llm-gateway/chat-completions) (Core concepts): Send simple messages and receive responses from LLM models - [Multi-turn Conversations](https://www.assemblyai.com/docs/llm-gateway/conversations) (Core concepts): Maintain context across multiple exchanges with conversation history - [Prompt Engineering for LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/prompt-engineering) (Core concepts): Learn how to improve your prompts for LLM Gateway. - [Rate limits](https://www.assemblyai.com/docs/llm-gateway/rate-limits) (Core concepts): Rate limits documentation. - [Troubleshooting](https://www.assemblyai.com/docs/llm-gateway/troubleshooting) (Core concepts): Common issues and fixes when using the LLM Gateway. - [Apply LLM Gateway to Audio Transcripts](https://www.assemblyai.com/docs/llm-gateway/apply-llms-to-audio-files) (Voice AI Guides): Learn how to analyze audio transcripts using LLM Gateway. - [Setup An AI Coach With LLM Gateway](https://www.assemblyai.com/docs/guides/task-endpoint-ai-coach) (Voice AI Guides > Basic LLM Gateway workflows): Setup An AI Coach With LLM Gateway documentation. - [Generate Action Items with LLM Gateway](https://www.assemblyai.com/docs/guides/task-endpoint-action-items) (Voice AI Guides > Basic LLM Gateway workflows): Generate Action Items with LLM Gateway documentation. - [Prompt A Structured Q&A Response Using LLM Gateway](https://www.assemblyai.com/docs/guides/task-endpoint-structured-QA) (Voice AI Guides > Basic LLM Gateway workflows): Prompt A Structured Q&A Response Using LLM Gateway documentation. - [Estimate Input Token Costs for LLM Gateway](https://www.assemblyai.com/docs/guides/counting-tokens) (Voice AI Guides > Basic LLM Gateway workflows): Estimate Input Token Costs for LLM Gateway documentation. - [Extract Dialogue Data with LLM Gateway and JSON](https://www.assemblyai.com/docs/guides/dialogue-data) (Voice AI Guides > Get quotes and citations with LLM Gateway): Extract Dialogue Data with LLM Gateway and JSON documentation. - [Extract Quotes with Timestamps Using LLM Gateway + Semantic Search](https://www.assemblyai.com/docs/guides/transcript-citations) (Voice AI Guides > Get quotes and citations with LLM Gateway): Extract Quotes with Timestamps Using LLM Gateway + Semantic Search documentation. - [Extract Transcript Quotes with LLM Gateway](https://www.assemblyai.com/docs/guides/timestamped-transcripts) (Voice AI Guides > Get quotes and citations with LLM Gateway): Extract Transcript Quotes with LLM Gateway documentation. - [Analyze The Sentiment Of A Customer Call using LLM Gateway](https://www.assemblyai.com/docs/guides/call-sentiment-analysis) (Voice AI Guides > Substitute Speech Understanding with LLM Gateway): Analyze The Sentiment Of A Customer Call using LLM Gateway documentation. - [Custom Topic Tags Using LLM Gateway](https://www.assemblyai.com/docs/guides/custom-topic-tags) (Voice AI Guides > Substitute Speech Understanding with LLM Gateway): Custom Topic Tags Using LLM Gateway documentation. - [Redact PII from Text Using LLM Gateway](https://www.assemblyai.com/docs/guides/llm-gateway-pii-redaction) (Voice AI Guides > Substitute Speech Understanding with LLM Gateway): Redact PII from Text Using LLM Gateway documentation. - [Apply LLM Gateway to Streaming](https://www.assemblyai.com/docs/guides/real_time_llm_gateway) (Voice AI Guides > Streaming with LLM Gateway): Learn how to analyze streaming audio transcripts using LLM Gateway. - [Translate Real-time STT Transcripts with LLM Gateway](https://www.assemblyai.com/docs/guides/real_time_translation) (Voice AI Guides > Streaming with LLM Gateway): Translate Real-time STT Transcripts with LLM Gateway documentation. - [Implement a Sales Playbook Using LLM Gateway](https://www.assemblyai.com/docs/guides/sales-playbook) (Voice AI Guides > Use-case specific LLM Gateway workflows): Implement a Sales Playbook Using LLM Gateway documentation. - [Segment A Phone Call using LLM Gateway](https://www.assemblyai.com/docs/guides/phone-call-segmentation) (Voice AI Guides > Use-case specific LLM Gateway workflows): Segment A Phone Call using LLM Gateway documentation. - [Generate SOAP Notes using LLM Gateway](https://www.assemblyai.com/docs/guides/soap-note-generation) (Voice AI Guides > Use-case specific LLM Gateway workflows): Generate SOAP Notes using LLM Gateway documentation. ## FAQ - [Frequently Asked Questions](https://www.assemblyai.com/docs/faq) (Overview): Find answers to common questions about AssemblyAI's services, features, and pricing. - [Has AssemblyAI certified to the EU-U.S. Data Privacy Framework?](https://www.assemblyai.com/docs/faq/has-assemblyai-certified-to-the-eu-us-data-privacy-framework) (Overview > Privacy & Security): Has AssemblyAI certified to the EU-U.S. Data Privacy Framework? documentation. - [Can I sign a DPA agreement with AssemblyAI?](https://www.assemblyai.com/docs/faq/can-i-sign-a-dpa-agreement-with-assemblyai) (Overview > Privacy & Security): Can I sign a DPA agreement with AssemblyAI? documentation. - [Can you provide a copy of your most recent penetration test executive summary?](https://www.assemblyai.com/docs/faq/can-you-provide-a-copy-of-your-most-recent-penetration-test-executive-summary) (Overview > Privacy & Security): Can you provide a copy of your most recent penetration test executive summary? documentation. - [Can you provide a recent vulnerability scan?](https://www.assemblyai.com/docs/faq/can-you-provide-a-recent-vulnerability-scan) (Overview > Privacy & Security): Can you provide a recent vulnerability scan? documentation. - [Will AssemblyAI sign a Business Associate Addendum (BAA) as described in the HIPAA rules and regulations?](https://www.assemblyai.com/docs/faq/can-you-sign-a-baa) (Overview > Privacy & Security): Will AssemblyAI sign a Business Associate Addendum (BAA) as described in the HIPAA rules and regulations? documentation. - [Do you have a formal risk assessment policy or process?](https://www.assemblyai.com/docs/faq/do-you-have-a-formal-risk-assessment-policy-or-process) (Overview > Privacy & Security): Do you have a formal risk assessment policy or process? documentation. - [Do you have documented information security policies? If so, how frequently are they updated?](https://www.assemblyai.com/docs/faq/do-you-have-documented-information-security-policies-if-so-how-frequently-are-they-updated) (Overview > Privacy & Security): Do you have documented information security policies? If so, how frequently are they updated? documentation. - [Do you offer EU Data Residency?](https://www.assemblyai.com/docs/faq/do-you-offer-eu-data-residency) (Overview > Privacy & Security): Do you offer EU Data Residency? documentation. - [Do you offer self-hosted solutions?](https://www.assemblyai.com/docs/faq/do-you-offer-self-hosted-solutions) (Overview > Privacy & Security): Do you offer self-hosted solutions? documentation. - [Do you offer servers in the EU?](https://www.assemblyai.com/docs/faq/do-you-offer-servers-in-the-eu) (Overview > Privacy & Security): Do you offer servers in the EU? documentation. - [Do you support SAML in your product?](https://www.assemblyai.com/docs/faq/do-you-support-saml-in-your-product) (Overview > Privacy & Security): Do you support SAML in your product? documentation. - [How long are outputs maintained?](https://www.assemblyai.com/docs/faq/how-long-are-outputs-retained) (Overview > Privacy & Security): How long are outputs maintained? documentation. - [Does AssemblyAI utilize an anti-virus/anti-malware solution across all relevant infrastructure (workstations and servers), and are appropriate response capabilities deployed to respond to alerts?](https://www.assemblyai.com/docs/faq/does-assemblyai-utilize-an-anti-virus-anti-malware-solution-across-all-relevant-infrastructure-workstations-and-servers-and-are-appropriate-response-capabilities-deployed-to-respond-to-ale) (Overview > Privacy & Security): Does AssemblyAI utilize an anti-virus/anti-malware solution across all relevant infrastructure (workstations and servers), and are appropriate response capabilities deployed to respond to alerts? documentation. - [How are incidents escalated within your organization?](https://www.assemblyai.com/docs/faq/how-are-incidents-escalated-within-your-organization) (Overview > Privacy & Security): How are incidents escalated within your organization? documentation. - [How do we securely use your service?](https://www.assemblyai.com/docs/faq/how-do-we-securely-use-your-service) (Overview > Privacy & Security): How do we securely use your service? documentation. - [How do you protect production code?](https://www.assemblyai.com/docs/faq/how-do-you-protect-production-code) (Overview > Privacy & Security): How do you protect production code? documentation. - [How to Access AssemblyAI's Security Reports](https://www.assemblyai.com/docs/faq/how-to-access-assemblyai-s-security-reports) (Overview > Privacy & Security): How to Access AssemblyAI's Security Reports documentation. - [How to Opt Out of Data Sharing for our Model Improvement Program](https://www.assemblyai.com/docs/faq/how-to-opt-out-of-data-sharing-for-our-model-improvement-program) (Overview > Privacy & Security): How to Opt Out of Data Sharing for our Model Improvement Program documentation. - [Is multi-factor authentication enforced for all access to scoped systems and data?](https://www.assemblyai.com/docs/faq/is-multi-factor-authentication-enforced-for-all-access-to-scoped-systems-and-data) (Overview > Privacy & Security): Is multi-factor authentication enforced for all access to scoped systems and data? documentation. - [Does AssemblyAI have a documented process for reviewing and approving third-party service providers?](https://www.assemblyai.com/docs/faq/is-there-a-documented-process-for-reviewing-and-approving-third-party-service-providers) (Overview > Privacy & Security): Does AssemblyAI have a documented process for reviewing and approving third-party service providers? documentation. - [Does AssemblyAI have an incident response plan?](https://www.assemblyai.com/docs/faq/please-describe-the-incident-response-plan) (Overview > Privacy & Security): Does AssemblyAI have an incident response plan? documentation. - [What are your recovery time and recovery point objectives?](https://www.assemblyai.com/docs/faq/what-are-your-recovery-time-and-recovery-point-objectives) (Overview > Privacy & Security): What are your recovery time and recovery point objectives? documentation. - [What is your SLA for repairing Critical/High/Medium vulnerabilities?](https://www.assemblyai.com/docs/faq/what-is-your-sla-for-repairing-critical-high-medium-vulnerabilities) (Overview > Privacy & Security): What is your SLA for repairing Critical/High/Medium vulnerabilities? documentation. - [What logs are available to customers?](https://www.assemblyai.com/docs/faq/what-logs-are-available-to-customers) (Overview > Privacy & Security): What logs are available to customers? documentation. - [What standards do your internal password policies follow?](https://www.assemblyai.com/docs/faq/what-standards-do-your-internal-password-policies-follow) (Overview > Privacy & Security): What standards do your internal password policies follow? documentation. - [Where are your servers located?](https://www.assemblyai.com/docs/faq/where-are-your-servers-located) (Overview > Privacy & Security): Where are your servers located? documentation. - [Am I charged for transcribing silent audio?](https://www.assemblyai.com/docs/faq/am-i-charged-for-transcribing-silent-audio) (Overview > Pre-recorded audio): Am I charged for transcribing silent audio? documentation. - [Are Custom Models More Accurate than General Models?](https://www.assemblyai.com/docs/faq/are-custom-models-more-accurate-than-general-models) (Overview > Pre-recorded audio): Are Custom Models More Accurate than General Models? documentation. - [Do I Get Charged for Failed API Calls?](https://www.assemblyai.com/docs/faq/are-customers-charged-for-api-calls-that-result-in-errors) (Overview > Pre-recorded audio): Do I Get Charged for Failed API Calls? documentation. - [Are there any limits on file size or file duration for files submitted to the API?](https://www.assemblyai.com/docs/faq/are-there-any-limits-on-file-size-or-file-duration-for-files-submitted-to-the-api) (Overview > Pre-recorded audio): Are there any limits on file size or file duration for files submitted to the API? documentation. - [Can I customize how words are spelled by the model?](https://www.assemblyai.com/docs/faq/can-i-customize-how-words-are-spelled-by-the-model) (Overview > Pre-recorded audio): Can I customize how words are spelled by the model? documentation. - [Can I delete the transcripts I have created using the API?](https://www.assemblyai.com/docs/faq/can-i-delete-the-transcripts-i-have-created-using-the-api) (Overview > Pre-recorded audio): Can I delete the transcripts I have created using the API? documentation. - [Can I get a list of all transcripts I have created?](https://www.assemblyai.com/docs/faq/can-i-get-a-list-of-all-transcripts-i-have-created) (Overview > Pre-recorded audio): Can I get a list of all transcripts I have created? documentation. - [Can I send audio to AssemblyAI in segments and still get speaker labels for the whole recording?](https://www.assemblyai.com/docs/faq/can-i-send-audio-to-assemblyai-in-segments-and-still-get-speaker-labels-for-the-whole-recording) (Overview > Pre-recorded audio): Can I send audio to AssemblyAI in segments and still get speaker labels for the whole recording? documentation. - [Can I submit files to the API that are stored in a Google Drive?](https://www.assemblyai.com/docs/faq/can-i-submit-files-to-the-api-that-are-stored-in-a-google-drive) (Overview > Pre-recorded audio): Can I submit files to the API that are stored in a Google Drive? documentation. - [Can I use the API without internet access?](https://www.assemblyai.com/docs/faq/can-i-use-the-api-without-internet-access) (Overview > Pre-recorded audio): Can I use the API without internet access? documentation. - [Do we have resources for building with Make?](https://www.assemblyai.com/docs/faq/do-we-have-resources-for-building-with-make-) (Overview > Pre-recorded audio): Do we have resources for building with Make? documentation. - [Do you have any examples for how to use your API?](https://www.assemblyai.com/docs/faq/do-you-have-any-examples-for-how-to-use-your-api-) (Overview > Pre-recorded audio): Do you have any examples for how to use your API? documentation. - [Do you have example use cases for using AssemblyAI?](https://www.assemblyai.com/docs/faq/do-you-have-example-use-cases-for-using-assemblyai-) (Overview > Pre-recorded audio): Do you have example use cases for using AssemblyAI? documentation. - [Do you offer cross-file Speaker Identification?](https://www.assemblyai.com/docs/faq/do-you-offer-cross-file-speaker-identification) (Overview > Pre-recorded audio): Do you offer cross-file Speaker Identification? documentation. - [Do you offer translation?](https://www.assemblyai.com/docs/faq/do-you-offer-translation) (Overview > Pre-recorded audio): Do you offer translation? documentation. - [Do you offer voice-to-voice or text-to-speech (TTS)?](https://www.assemblyai.com/docs/faq/do-you-offer-voice-to-voice-or-text-to-speech-tts) (Overview > Pre-recorded audio): Do you offer voice-to-voice or text-to-speech (TTS)? documentation. - [Does it cost extra to export SRT or VTT captions?](https://www.assemblyai.com/docs/faq/does-it-cost-extra-to-export-srt-or-vtt-captions) (Overview > Pre-recorded audio): Does it cost extra to export SRT or VTT captions? documentation. - [Is there a way to generate SRT or VTT captions with speaker labels?](https://www.assemblyai.com/docs/faq/is-there-a-way-to-generate-srt-or-vtt-captions-with-speaker-labels) (Overview > Pre-recorded audio): Is there a way to generate SRT or VTT captions with speaker labels? documentation. - [Does it cost more to transcribe an audio or video?](https://www.assemblyai.com/docs/faq/does-it-cost-more-to-transcribe-an-audio-or-video) (Overview > Pre-recorded audio): Does it cost more to transcribe an audio or video? documentation. - [Does your API return timestamps for individual words?](https://www.assemblyai.com/docs/faq/does-your-api-return-timestamps-for-individual-words) (Overview > Pre-recorded audio): Does your API return timestamps for individual words? documentation. - [How are individual speakers identified and how does the Speaker Label feature work?](https://www.assemblyai.com/docs/faq/how-are-individual-speakers-identified-and-how-does-the-speaker-label-feature-work) (Overview > Pre-recorded audio): How are individual speakers identified and how does the Speaker Label feature work? documentation. - [How are paragraphs created for the /paragraphs endpoint?](https://www.assemblyai.com/docs/faq/how-are-paragraphs-created-for-the-paragraphs-endpoint) (Overview > Pre-recorded audio): How are paragraphs created for the /paragraphs endpoint? documentation. - [How are word/transcript level confidence scores calculated?](https://www.assemblyai.com/docs/faq/how-are-word-transcript-level-confidence-scores-calculated) (Overview > Pre-recorded audio): How are word/transcript level confidence scores calculated? documentation. - [How can I integrate AssemblyAI with other services?](https://www.assemblyai.com/docs/faq/how-can-i-integrate-assemblyai-with-other-services-) (Overview > Pre-recorded audio): How can I integrate AssemblyAI with other services? documentation. - [How can I make certain words more likely to be transcribed?](https://www.assemblyai.com/docs/faq/how-can-i-make-certain-words-more-likely-to-be-transcribed) (Overview > Pre-recorded audio): How can I make certain words more likely to be transcribed? documentation. - [How can I test AssemblyAI without writing code?](https://www.assemblyai.com/docs/faq/how-can-i-test-assemblyai-without-writing-code-) (Overview > Pre-recorded audio): How can I test AssemblyAI without writing code? documentation. - [How can I transcribe YouTube videos?](https://www.assemblyai.com/docs/faq/how-can-i-transcribe-youtube-videos) (Overview > Pre-recorded audio): How can I transcribe YouTube videos? documentation. - [How do I generate subtitles?](https://www.assemblyai.com/docs/faq/how-do-i-generate-subtitles) (Overview > Pre-recorded audio): How do I generate subtitles? documentation. - [How does AssemblyAI compare to other ASR providers?](https://www.assemblyai.com/docs/faq/how-does-assemblyai-compare-to-other-asr-providers) (Overview > Pre-recorded audio): How does AssemblyAI compare to other ASR providers? documentation. - [How does Automatic Language Detection work?](https://www.assemblyai.com/docs/faq/how-does-language-detection-work-for-transcriptions) (Overview > Pre-recorded audio): How does Automatic Language Detection work? documentation. - [How does the API handle files that contain spoken audio in multiple languages?](https://www.assemblyai.com/docs/faq/how-does-the-api-handle-files-that-contain-spoken-audio-in-multiple-languages) (Overview > Pre-recorded audio): How does the API handle files that contain spoken audio in multiple languages? documentation. - [How long does it take to transcribe a file?](https://www.assemblyai.com/docs/faq/how-long-does-it-take-to-transcribe-a-file) (Overview > Pre-recorded audio): How long does it take to transcribe a file? documentation. - [What should I do if I'm getting an error?](https://www.assemblyai.com/docs/faq/i-am-getting-an-error-what-should-i-do) (Overview > Pre-recorded audio): What should I do if I'm getting an error? documentation. - [Is there a Postman collection for using the API?](https://www.assemblyai.com/docs/faq/is-there-a-postman-collection-for-using-the-api) (Overview > Pre-recorded audio): Is there a Postman collection for using the API? documentation. - [Is there a way for us to send the start time / end time for transcription instead of transcribing the whole length of a call recording?](https://www.assemblyai.com/docs/faq/is-there-a-way-for-us-to-send-the-start-time-end-time-for-transcription-instead-of-transcribing-the-whole-length-of-a-call-recording) (Overview > Pre-recorded audio): Is there a way for us to send the start time / end time for transcription instead of transcribing the whole length of a call recording? documentation. - [Is there an OpenAPI spec/schema for the API?](https://www.assemblyai.com/docs/faq/is-there-an-openapi-spec-schema-for-the-api) (Overview > Pre-recorded audio): Is there an OpenAPI spec/schema for the API? documentation. - [What causes a "read operation timed out" error?](https://www.assemblyai.com/docs/faq/read-operation-timed-out-error) (Overview > Pre-recorded audio): What causes a "read operation timed out" error? documentation. - [Should I use Speaker Labels or Multi-channel?](https://www.assemblyai.com/docs/faq/should-i-use-speaker-labels-or-multi-channel) (Overview > Pre-recorded audio): Should I use Speaker Labels or Multi-channel? documentation. - [Should I use the NA or EU endpoint for my Speech-to-Text requests?](https://www.assemblyai.com/docs/faq/should-i-use-the-na-or-eu-endpoint) (Overview > Pre-recorded audio): Should I use the NA or EU endpoint for my Speech-to-Text requests? documentation. - [What are the recommended options for audio noise reduction?](https://www.assemblyai.com/docs/faq/what-are-the-recommended-options-for-audio-noise-reduction) (Overview > Pre-recorded audio): What are the recommended options for audio noise reduction? documentation. - [What audio and video file types are supported by your API?](https://www.assemblyai.com/docs/faq/what-audio-and-video-file-types-are-supported-by-your-api) (Overview > Pre-recorded audio): What audio and video file types are supported by your API? documentation. - [What IP Address Should I Whitelist for AssemblyAI?](https://www.assemblyai.com/docs/faq/what-ip-address-should-i-whitelist-for-assemblyai) (Overview > Pre-recorded audio): What IP Address Should I Whitelist for AssemblyAI? documentation. - [What is the minimum audio duration that the API can transcribe?](https://www.assemblyai.com/docs/faq/what-is-the-minimum-audio-duration-that-the-api-can-transcribe) (Overview > Pre-recorded audio): What is the minimum audio duration that the API can transcribe? documentation. - [What is the recommended file type for using your API?](https://www.assemblyai.com/docs/faq/what-is-the-recommended-file-type-for-using-your-api) (Overview > Pre-recorded audio): What is the recommended file type for using your API? documentation. - [What types of audio URLs can I use with the API?](https://www.assemblyai.com/docs/faq/what-types-of-audio-urls-can-i-use-with-the-api) (Overview > Pre-recorded audio): What types of audio URLs can I use with the API? documentation. - [Where can I find a list of recent changes to the API?](https://www.assemblyai.com/docs/faq/where-can-i-find-a-list-of-recent-changes-to-the-api) (Overview > Pre-recorded audio): Where can I find a list of recent changes to the API? documentation. - [Where can I find cURL code examples?](https://www.assemblyai.com/docs/faq/where-can-i-find-curl-code-examples) (Overview > Pre-recorded audio): Where can I find cURL code examples? documentation. - [Why can't I access recording URLs from the /upload endpoint directly?](https://www.assemblyai.com/docs/faq/why-cant-i-access-urls-from-the-upload-endpoint-directly) (Overview > Pre-recorded audio): Why can't I access recording URLs from the /upload endpoint directly? documentation. - [Can I use speaker diarization with Streaming Speech-to-Text?](https://www.assemblyai.com/docs/faq/can-i-use-speaker-diarization-with-live-audio-transcription) (Overview > Streaming audio): Can I use speaker diarization with Streaming Speech-to-Text? documentation. - [How accurate is your Streaming transcription compared to Async transcription?](https://www.assemblyai.com/docs/faq/how-accurate-is-your-real-time-transcription-compared-to-async-transcription) (Overview > Streaming audio): How accurate is your Streaming transcription compared to Async transcription? documentation. - [How does Universal Streaming session-based pricing work?](https://www.assemblyai.com/docs/faq/how-does-universal-streaming-session-based-pricing-work) (Overview > Streaming audio): How does Universal Streaming session-based pricing work? documentation. - [What languages are supported for Streaming Speech-to-text?](https://www.assemblyai.com/docs/faq/language-support-for-real-time-transcription) (Overview > Streaming audio): What languages are supported for Streaming Speech-to-text? documentation. - [Resolving SSL Certificate Verification Error When Trying to Use Real-time STT](https://www.assemblyai.com/docs/faq/resolving-ssl-certificate-verification-error-in-assemblyai-real-time-transcriber) (Overview > Streaming audio): Resolving SSL Certificate Verification Error When Trying to Use Streaming STT documentation. - [I am getting a "Model deprecated. See docs for new model information" error message. What does it mean?](https://www.assemblyai.com/docs/faq/upgrading-to-the-universal-streaming-model) (Overview > Streaming audio): I am getting a "Model deprecated. See docs for new model information" error message. What does it mean? documentation. - [How do Content Moderation severity scores work?](https://www.assemblyai.com/docs/faq/how-do-content-moderation-severity-scores-work) (Overview > Speech understanding): How do Content Moderation severity scores work? documentation. - [How can I summarize my audio file?](https://www.assemblyai.com/docs/faq/how-do-your-summarization-models-work) (Overview > Speech understanding): How can I summarize my audio file? documentation. - [Is Mistral still supported?](https://www.assemblyai.com/docs/faq/is-mistral-still-supported) (Overview > Speech understanding): Is Mistral still supported? documentation. - [Is pricing for Speech Understanding per feature or all-inclusive?](https://www.assemblyai.com/docs/faq/is-pricing-for-audio-intelligence-per-feature-or-all-inclusive) (Overview > Speech understanding): Is pricing for Speech Understanding per feature or all-inclusive? documentation. - [Understanding Input and Output Tokens for LLM Gateway](https://www.assemblyai.com/docs/faq/understanding-input-and-output-tokens-for-llm-gateway) (Overview > LLM Gateway): Understanding Input and Output Tokens for LLM Gateway documentation. - [Can you use the Playground with files in languages other than English?](https://www.assemblyai.com/docs/faq/can-you-use-the-playground-with-files-in-languages-other-than-english) (Overview > Playground): Can you use the Playground with files in languages other than English? documentation. - [How do I delete a transcript I created using the Playground?](https://www.assemblyai.com/docs/faq/how-do-i-delete-a-transcript-i-created-using-the-playground) (Overview > Playground): How do I delete a transcript I created using the Playground? documentation. - [Why is the transcription I am receiving using the Playground in a different language?](https://www.assemblyai.com/docs/faq/why-is-the-transcription-i-am-receiving-using-the-playground-in-a-different-language) (Overview > Playground): Why is the transcription I am receiving using the Playground in a different language? documentation. - [Do you have an affiliate marketing program?](https://www.assemblyai.com/docs/faq/do-you-have-an-affiliate-marketing-program) (Overview > Company): Do you have an affiliate marketing program? documentation. - [Do you have any job openings or internship opportunities?](https://www.assemblyai.com/docs/faq/do-you-have-any-job-openings-or-internship-opportunities) (Overview > Company): Do you have any job openings or internship opportunities? documentation. - [How do I contact support?](https://www.assemblyai.com/docs/faq/how-do-i-contact-support) (Overview > Company): How do I contact support? documentation. - [How do I get in touch with your Sales team?](https://www.assemblyai.com/docs/faq/how-do-i-get-in-touch-with-your-sales-team) (Overview > Company): How do I get in touch with your Sales team? documentation. - [I’ve spotted an issue with the website, what should I do?](https://www.assemblyai.com/docs/faq/ive-spotted-an-issue-with-the-website-what-should-i-do) (Overview > Company): I’ve spotted an issue with the website, what should I do? documentation. - [What are your support hours and response time SLAs?](https://www.assemblyai.com/docs/faq/what-are-your-support-hours-and-response-time-slas) (Overview > Company): What are your support hours and response time SLAs? documentation. - [What is your API Uptime SLA?](https://www.assemblyai.com/docs/faq/what-is-your-api-uptime-sla) (Overview > Company): What is your API Uptime SLA? documentation. - [Where can I find AssemblyAI's product roadmap?](https://www.assemblyai.com/docs/faq/where-can-i-find-assemblyais-product-roadmap) (Overview > Company): Where can I find AssemblyAI's product roadmap? documentation. ## Additional pages - [AssemblyAI integration prompt for AI coding agents](https://www.assemblyai.com/docs/agent-instructions): The full integration prompt AI coding agents fetch when building with AssemblyAI. Pin the URL https://www.assemblyai.com/docs/agent-instructions.md in your agent's project instructions, or copy the prompt below. - [Deployment](https://www.assemblyai.com/docs/deployment): Take AssemblyAI to production with these best practices. - [Select The EU Region for EU Data Residency](https://www.assemblyai.com/docs/pre-recorded-audio/guides/how_to_use_the_eu_endpoint): Select The EU Region for EU Data Residency documentation. - [Identifying speakers in audio recordings](https://www.assemblyai.com/docs/pre-recorded-audio/guides/identifying-speakers-in-audio-recordings): Add speaker labels to your transcript - [Streaming v2 (Legacy)](https://www.assemblyai.com/docs/pre-recorded-audio/legacy-streaming): Transcribe live audio with Streaming Speech-to-Text - [Universal-3.5 Pro](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-5-pro): Set up and configure Universal-3.5 Pro for pre-recorded audio transcription. - [Tracking customer transcription usage](https://www.assemblyai.com/docs/tracking-your-customers-usage): Learn how to track individual customer usage within your product using AssemblyAI's webhook system and metadata. - [Use case guides](https://www.assemblyai.com/docs/use-cases): Build real-world applications with AssemblyAI. - [Universal-3.5 Pro Streaming API](https://www.assemblyai.com/docs/voice-agents/universal-3-5-pro-streaming-api): Build a custom voice agent on AssemblyAI's streaming WebSocket with turn detection, barge-in, and interruption handling without a third-party orchestrator. - [Create a webhook subscription](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/create-webhook-subscription): Create a webhook subscription for Voice Agent API events. - [Delete a webhook subscription](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/delete-webhook-subscription): Delete a webhook subscription. - [Retrieve a webhook subscription](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/get-webhook-subscription): Retrieve a webhook subscription by ID. - [List webhook subscriptions](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/list-webhook-subscriptions): List all webhook subscriptions in your account. - [Update a webhook subscription](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/api-spec/update-webhook-subscription): Update a webhook subscription. - [Webhooks](https://www.assemblyai.com/docs/voice-agents/voice-agent-api/webhooks): Subscribe to session and call lifecycle events for your agents. AssemblyAI POSTs a signed JSON payload to your URL when each event fires. ## API specs - [docs/openapi.yaml](https://www.assemblyai.com/docs/openapi.yaml): API specification source used by the docs. - [docs/api-reference/specs/llm-gateway.yaml](https://www.assemblyai.com/docs/api-reference/specs/llm-gateway.yaml): API specification source used by the docs. - [docs/api-reference/specs/streaming-token.yaml](https://www.assemblyai.com/docs/api-reference/specs/streaming-token.yaml): API specification source used by the docs. - [docs/api-reference/specs/voice-agent-token.yaml](https://www.assemblyai.com/docs/api-reference/specs/voice-agent-token.yaml): API specification source used by the docs. - [docs/api-reference/specs/agents.yaml](https://www.assemblyai.com/docs/api-reference/specs/agents.yaml): API specification source used by the docs. - [docs/api-reference/specs/webhooks.yaml](https://www.assemblyai.com/docs/api-reference/specs/webhooks.yaml): API specification source used by the docs. - [docs/api-reference/specs/streaming.yaml](https://www.assemblyai.com/docs/api-reference/specs/streaming.yaml): API specification source used by the docs. - [docs/api-reference/specs/voice-agent-api.yaml](https://www.assemblyai.com/docs/api-reference/specs/voice-agent-api.yaml): API specification source used by the docs.