AI-powered5 credits / call
POST /api/v1/tools/transcribeAudio Transcription
Speech to text via OpenAI Whisper-1
Transcribe any audio file to text. Auto-detects language from 50+ options. Optional word-level timestamps for caption sync. Works on interviews, meetings, podcasts, and voice memos.
How it works
Sends your audio to Whisper-1. Returns transcript, detected language, confidence, duration, and optional per-word and per-segment timestamps.
What you could build
MeetingMemo
Auto-summary for every recorded meeting
$3K–$6K MRR
est. MRR
PodCap
Automatic podcast transcription and caption export
$1K–$4K MRR
est. MRR
VoiceNotes
Voice memo to structured note for mobile apps
$500–$2K MRR
est. MRR
Parameters
audiorequiredAudio file — mp3, wav, m4a, webm, flac, ogg — max 25MB· e.g.
meeting.mp3languageoptionalISO-639-1 language hint to improve accuracy (omit to auto-detect)· e.g.
entimestampsoptionalReturn word-level and segment-level timestamps· e.g.
truepromptoptionalContext hint to improve accuracy for domain-specific terms· e.g.
Technical meeting about API designExample request
Example response
Ready to use Audio Transcription?
Free plan — 100 calls/month, no credit card.