# Changelog of Public Audio Speech Transcription (`automation-lab/public-audio-speech-transcription`) Actor

- **URL**: https://apify.com/automation-lab/public-audio-speech-transcription/changelog.md
- **Full Actor documentation**: https://apify.com/automation-lab/public-audio-speech-transcription.md

## Changelog

### 0.1.0 — 2026-10-24

- Transcribe direct public audio-only files with language detection and speech segment timing.
- Optionally include approximate word timing and confidence.
- Open a transcript overview or the full JSON export, including optional words and language confidence.
- Reject private destinations, signed links, video streams and oversized or over-duration files.
- Uses the lightweight multilingual Whisper tiny model; review recognition before relying on it.