Audio transcription API: transcribe any public audio URL (mp3, wav, m4a, ogg — up to 25MB / ~20 min) to text with a neural speech-recognition engine running locally on our hardware. Multilingual (~99 languages), auto language detection. Use as a speech-to-text step for voicemail, podcasts, meetings, and voice agents. Audio is processed in a sandbox and deleted immediately; we keep nothing.
| Network | Scheme | Amount | Pay To |
|---|---|---|---|
| Base | exact | $0.03 USDC | 0x8503...9432 |