Speech-to-text
Scribe One — speech to text
Scribe One turns audio into text for 1 credit per started minute of audio: voice messages, call-mode turns, recordings up to 8 MB. Language is detected automatically. Paired with eroq Voice One or eroq Voice Turbo it closes the loop for spoken conversations with a character.
40 free credits · no card · private mode on every account
- Price
- 1 credit / started minute
- Input
- Audio file up to 8 MB (≈ 8 minutes compressed)
- Languages
- Automatic detection
- Endpoint
- POST /v1/audio/transcriptions
- Access
- Every account
A call mode in three calls
Record the user, transcribe with Scribe One, answer with eroq RP+ and speak the reply with eroq Voice Turbo. Three requests, one key, one credit balance — the pattern behind voice modes in companion apps and interactive fiction.
Frequently asked questions
What audio formats does Scribe One accept?
wav or mp3, up to 8 MB per request, sent as multipart form data. Other containers (m4a, ogg, webm) are rejected with unsupported_format — re-encode client-side, or record WAV through WebAudio.
Is it priced per minute?
Yes — 1 credit per started minute of audio, read from the file itself. A 20-second voice note is 1 credit, a 2.5-minute recording 3. The response reports the measured audio_seconds next to credits_spent.
Keep exploring