# Speech-to-text (STT)

> Speech-to-text transcribes spoken audio into written text. Paired with a chat model and TTS it forms a voice conversation loop.

Language detection, file size caps and pricing per request or per minute are the practical parameters.

## On eroq

Scribe One: 5 credits per request, audio up to 8 MB, automatic language detection.

## FAQ

### What does transcription cost?

A flat 5 credits per request on Scribe One.

## Related

- https://eroq.ai/models/eroq-scribe-one — Scribe One
- https://eroq.ai/use-cases/ai-companion-apps — Companion apps

---

This page as HTML: https://eroq.ai/glossary/speech-to-text · Studio: https://eroq.ai/studio · Docs: https://eroq.ai/docs · Machine index: https://eroq.ai/llms.txt