Transcribe live audio

from assemblyai.sync.v1 import SyncTranscriber, SyncTranscriptionConfig

transcriber = SyncTranscriber()
config = SyncTranscriptionConfig(sample_rate=16000, channels=1)

# Push style, for callback sources (mic, WebRTC, telephony):
session = transcriber.open_live(config)
for chunk in microphone():   # your live PCM source
    session.write(chunk)
session.close()
print(session.result().text)

# Or pull style, from an iterable or stream you already have:
# result = transcriber.transcribe_live(microphone(), config=config)

{
  "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
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "detail": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "detail": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

POST

transcribe

live

from assemblyai.sync.v1 import SyncTranscriber, SyncTranscriptionConfig

transcriber = SyncTranscriber()
config = SyncTranscriptionConfig(sample_rate=16000, channels=1)

# Push style, for callback sources (mic, WebRTC, telephony):
session = transcriber.open_live(config)
for chunk in microphone():   # your live PCM source
    session.write(chunk)
session.close()
print(session.result().text)

# Or pull style, from an iterable or stream you already have:
# result = transcriber.transcribe_live(microphone(), config=config)

{
  "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
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "detail": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "detail": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

{
  "error_code": "bad_audio",
  "message": "<string>"
}

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

config

object

required

Transcription configuration. Must be the first part, ahead of audio. Send an empty object ({}) when you have no options to set.

Show child attributes

audio

file

required

Audio bytes, uploaded in chunks as they are produced. Set the part's Content-Type to audio/pcm for raw S16LE little-endian PCM (the usual live source) or audio/wav for a WAV stream.

Response

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.

Getting started

Features

API reference

Advanced

Transcribe live audio

Authorizations

Headers

Query Parameters

Body

Response