Transcription
Turn spoken audio into text.
POST /v1/audio/transcriptions submits a speech to text job. It takes JSON with the audio as an
https URL, not a file upload. It answers 202 with a job; see
How media jobs work for polling and output.
curl https://api.opinference.com/v1/audio/transcriptions \
-H "Authorization: Bearer $OP_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "cohere/transcribe",
"audio": "https://example.com/interview.mp3",
"language": "en"
}'Inputs
| Input | Meaning |
|---|---|
audio | The recording, as an https URL the gateway can download. See Inputs |
language | The spoken language, where the model asks for one |
Output
The transcript is a file in output[] with type text/plain. Download it from its url like
any other output.