Speech to Text

Upload an audio file and get the transcription text of the audio.

Limitations:

• Maximum audio duration: Files longer than 10 minutes will be trimmed to first 10 minutes
• Supported formats: MP3, WAV, OGG, M4A, AAC
• Large files are supported but only first 10 minutes will be transcribed

Note: For files larger than 100MB, please use chunked upload or consider splitting the audio file.

POST /tasks/stt

Speech To Text

cURL

curl --request POST \
  --url https://api.sunbird.ai/tasks/stt \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form audio='@example-file' \
  --form language=lug \
  --form adapter=lug \
  --form recognise_speakers=false \
  --form whisper=false

200

{
  "audio_transcription": "<string>",
  "diarization_output": {},
  "formatted_diarization_output": "<string>",
  "audio_transcription_id": 123,
  "audio_url": "<string>",
  "language": "<string>",
  "was_audio_trimmed": false,
  "original_duration_minutes": 123
}

Authorizations

Authorization · string · header · required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

multipart/form-data

audio · file · required

Audio file to transcribe

language · enum<string> · default: lug

Available options: ach, teo, eng, lug, lgg, nyn, swa, kin, xog, myx

adapter · enum<string> · default: lug

Available options: ach, teo, eng, lug, lgg, nyn, swa, kin, xog, myx

recognise_speakers · boolean · default: false

whisper · boolean · default: false

Response

200

application/json

Successful Response

changes

audio_transcription · string | null

diarization_output · Diarization Output · object

formatted_diarization_output · string | null

audio_transcription_id · integer | null

audio_url · string | null

language · string | null

was_audio_trimmed · boolean | null · default: false

original_duration_minutes · number | null