Transcribe a short audio file

POST /v1/transcribe

Python

Python SDK

import os from assemblyai.sync.v1 import SyncTranscriber transcriber = SyncTranscriber(api_key=os.environ["ASSEMBLYAI_API_KEY"]) transcriber.warm() # open the connection ahead of the request result = transcriber.transcribe("./sample.wav") print(result.text)

200

{
  "text": "Hi, I'm calling about my Best Buy order...",
  "words": [
    {
      "text": "Hi",
      "confidence": 0.91
    },
    {
      "text": "I'm",
      "confidence": 0.88
    }
  ],
  "confidence": 0.87,
  "audio_duration_ms": 101567,
  "session_id": "eb92c4ff-4bbb-429f-9b99-7279d7fe738f",
  "request_time_ms": 243.7
}

Authorizations

Authorization · string · header · required

Your AssemblyAI API key. Optionally prefixed with Bearer . Also accepted as the token query parameter.

Headers

X-AAI-Model · enum<string> · required

Model identifier used for request routing. The canonical value is universal-3-5-pro; u3-sync-pro and u3-pro are accepted as legacy aliases.

Available options: universal-3-5-pro

Query Parameters

token · string

API key alternative for clients that cannot set the Authorization header. The header wins when both are present.

Body

multipart/form-data

audio · file · required

Raw audio bytes. Set the part's Content-Type to audio/wav for WAV files or audio/pcm for raw S16LE little-endian PCM. Compressed audio is also accepted: audio/aac, audio/mpeg (MP3), audio/mp4 (M4A), audio/ogg (Ogg/Opus), audio/flac, or audio/webm.

config · object

Optional transcription configuration.

Show child attributes

Response

200

application/json

Transcription completed successfully.

text · string · required

Full transcript of the audio.

words · object[] · required

Per-word confidence scores, plus start/end timestamps when the request sets timestamps to true.

Show child attributes

confidence · number<float> · required

Overall transcript confidence (0–1).

audio_duration_ms · integer · required

Duration of the submitted audio in milliseconds.

session_id · string<uuid> · required

Server-generated request identifier. Include this in support requests.

request_time_ms · number<float>

End-to-end server-side processing time for the request in milliseconds, covering queue wait, decoding, and inference.