Skip to main content
POST
string
required
Transcription model. Currently: whisper-1.
file
required
Audio file to transcribe. Supported: mp3, mp4, mpeg, mpga, m4a, wav, webm. Max 25MB.
string
ISO-639-1 language code (e.g. en, ja, fr, de, es). Providing this improves accuracy and speed.
string
Optional text to guide the model’s style or continue a previous segment.
string
default:"json"
Output format. Options: json, text, srt (subtitles), vtt (web subtitles), verbose_json.
number
default:"0"
Sampling temperature 01. 0 for deterministic output.