Transcribe dictated audio

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"

result = aai.DictationTranscriber().transcribe_live("clip.wav")

print(result.text)          # verbatim transcript
print(result.llm_response)  # default cleanup rewrite
print(result.final_text)    # the rewrite, falling back to the transcript

{
  "text": "Um, patient presents with, uh, a persistent cough for about two weeks.",
  "words": [
    {
      "text": "Um",
      "confidence": 0.82
    },
    {
      "text": "patient",
      "confidence": 0.97
    },
    {
      "text": "presents",
      "confidence": 0.96
    }
  ],
  "confidence": 0.94,
  "llm_response": "Patient presents with a persistent cough for about two weeks.",
  "llm_error": null,
  "audio_duration_ms": 5120,
  "session_id": "eb92c4ff-4bbb-429f-9b99-7279d7fe738f",
  "request_time_ms": 812.4,
  "sync_time_ms": 430.1
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "status": 404,
  "title": "Not Found",
  "detail": "Invalid API key"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "status": 123,
  "title": "<string>",
  "detail": "<string>"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

POST

transcribe

live

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"

result = aai.DictationTranscriber().transcribe_live("clip.wav")

print(result.text)          # verbatim transcript
print(result.llm_response)  # default cleanup rewrite
print(result.final_text)    # the rewrite, falling back to the transcript

{
  "text": "Um, patient presents with, uh, a persistent cough for about two weeks.",
  "words": [
    {
      "text": "Um",
      "confidence": 0.82
    },
    {
      "text": "patient",
      "confidence": 0.97
    },
    {
      "text": "presents",
      "confidence": 0.96
    }
  ],
  "confidence": 0.94,
  "llm_response": "Patient presents with a persistent cough for about two weeks.",
  "llm_error": null,
  "audio_duration_ms": 5120,
  "session_id": "eb92c4ff-4bbb-429f-9b99-7279d7fe738f",
  "request_time_ms": 812.4,
  "sync_time_ms": 430.1
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "status": 404,
  "title": "Not Found",
  "detail": "Invalid API key"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "status": 123,
  "title": "<string>",
  "detail": "<string>"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

{
  "error": "<string>",
  "error_code": "bad_request"
}

Authorizations

Authorization

string

header

required

Your AssemblyAI API key, sent as the raw key with no Bearer prefix. An invalid key returns 404, not 401.

Body

multipart/form-data

config

object

required

Transcription and rewrite configuration. Must be the first part, ahead of audio. Send an empty object ({}) to transcribe with defaults, including the default rewrite. Unknown fields are forwarded to the transcription engine as-is, so transcription parameters added in future work without dictation-side changes.

Show child attributes

audio

file

required

Audio bytes, at most 120 seconds. Set the part's Content-Type to audio/wav for WAV or audio/pcm for raw 16-bit PCM. Compressed formats (MP3, M4A, FLAC, OGG, WebM) are rejected with 415. The part may be uploaded in chunks as the audio is captured.

Response

Transcription completed. The rewrite is best-effort: a failed rewrite still returns 200 with the transcription, llm_response set to null, and llm_error set. Fall back to text in that case, and never treat a non-null llm_error as a failed request.

text

string

required

The verbatim transcript. Never altered by the LLM.

words

object[]

required

Per-word transcript objects.

Show child attributes

confidence

number<float>

required

Overall transcription confidence (0–1).

audio_duration_ms

number

required

Duration of the submitted audio in milliseconds.

session_id

string<uuid>

required

Server-generated request identifier. Include it when reporting problems.

llm_response

string | null

The rewritten text, or null when the rewrite failed. Fall back to text when it is null.

llm_error

enum<string> | null

Set when the rewrite failed. timeout means the rewrite passed its 5-second internal deadline. null on success.

Available options:

timeout,

error

request_time_ms

number<float>

Total server-side processing time in milliseconds.

sync_time_ms

number<float>

The transcription portion of request_time_ms, in milliseconds.

Getting started

Features

API reference

Advanced

Transcribe dictated audio

Authorizations

Body

Response