Audio transcription

Use openai/gpt-transcribe for high-accuracy speech-to-text from completed audio files. The endpoint accepts OpenAI-compatible multipart requests and returns text. Files can be up to 25 MB.

Transcribe a file

curl https://api.impossibl.com/v1/audio/transcriptions \
  -H "Authorization: Bearer imp-rt-..." \
  -F file=@/path/to/audio.wav \
  -F model=openai/gpt-transcribe

{
  "text": "Bonjour, pouvez-vous m'entendre ?",
  "languages": [{ "code": "fr" }]
}

The gateway bills successful requests at $0.0045 per audio minute. Failed upstream requests and cancelled streams are not charged.

Add transcription context

Use prompt for unstructured recording context, keywords[] for expected terms, and languages[] for expected language codes.

curl https://api.impossibl.com/v1/audio/transcriptions \
  -H "Authorization: Bearer imp-rt-..." \
  -F file=@/path/to/audio.wav \
  -F model=openai/gpt-transcribe \
  -F 'prompt=a support call about account AC-42' \
  -F 'keywords[]=AC-42' \
  -F 'keywords[]=billing' \
  -F 'languages[]=en' \
  -F 'languages[]=fr'

For this model, use languages[], not the singular language field.

Stream a completed file

Set stream=true to receive transcript.text.delta events followed by a final transcript.text.done event.

curl -N https://api.impossibl.com/v1/audio/transcriptions \
  -H "Authorization: Bearer imp-rt-..." \
  -F file=@/path/to/audio.wav \
  -F model=openai/gpt-transcribe \
  -F stream=true

Get started

Core concepts

Using the API

Transcribe a file

Add transcription context

Stream a completed file

​Transcribe a file

​Add transcription context

​Stream a completed file

Transcribe a file

Add transcription context

Stream a completed file