Skip to main content
GET
/
api
/
v1
/
llm
/
speech
/
transcriptions
/
history
/
{stt_id}
Python (SDK)
from meetkai_mka1 import SDK


with SDK(
    bearer_auth="<YOUR_BEARER_TOKEN_HERE>",
) as sdk:

    res = sdk.llm.speech.get_transcription_history(stt_id="stt_aa87e2b1112a455b8deabed784372198")

    # Handle response
    print(res)
{
  "id": "stt_aa87e2b1112a455b8deabed784372198",
  "object": "speech.transcription",
  "text": "Hello, this is a sample transcription of the audio file.",
  "language": "en",
  "confidence": 0.95,
  "model": "auto",
  "provider_id": "azure",
  "filename": "audio.wav",
  "audio_bytes": 120000,
  "audio_mime_type": "audio/wav",
  "speakers": null,
  "streaming": false,
  "metadata": {},
  "created_at": 1704067200
}

Authorizations

Authorization
string
header
required

Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.

Headers

X-On-Behalf-Of
string

Optional external end-user identifier forwarded by the API gateway.

Path Parameters

stt_id
string
required

Response

200 - application/json

OK

A stored speech-to-text transcription.

id
string
required

Unique identifier for the history item.

object
any
required

The object type, always 'speech.transcription'.

text
string
required

The transcribed text.

language
string | null
required

The detected or specified language code.

confidence
number | null
required

Confidence score from 0 to 1, when available.

model
string
required

The transcription model used.

provider_id
string | null
required

The provider that produced the transcription.

filename
string | null
required

Original filename of the input audio, when available.

audio_bytes
integer
required

Size of the input audio in bytes.

Required range: -9007199254740991 <= x <= 9007199254740991
audio_mime_type
string | null
required

MIME type of the stored input audio.

speakers
object[] | null
required

Speaker diarization segments, when present.

streaming
boolean
required

Whether the transcription came from the streaming WebSocket.

metadata
object
required

Arbitrary metadata stored with the item.

created_at
integer
required

Unix timestamp (seconds) when the item was created.

Required range: -9007199254740991 <= x <= 9007199254740991