# Changelog of Audio Speech-to-Text Transcriber (`automation-lab/audio-speech-to-text-transcriber`) Actor

- **URL**: https://apify.com/automation-lab/audio-speech-to-text-transcriber/changelog.md
- **Full Actor documentation**: https://apify.com/automation-lab/audio-speech-to-text-transcriber.md

## Changelog

### 0.1.6 — 2026-09-15

- Faster multi-file transcription: batches now load the local Whisper model once per run and reuse it across every media URL, reducing repeated startup work while preserving outputs, ordering, subtitle files, failure records, and billing behavior.

### 0.1.0

- Added local speech-to-text inference for direct public audio and video file URLs.
- Added automatic language detection, complete transcript text, and timestamped segments.
- Added optional SRT and VTT subtitle artifacts.
- Added bounded file-size and duration controls, DNS-rebinding-safe public-network URL validation on every initial and redirected connection, and per-URL error records.
- Initial release uses the multilingual Whisper `tiny` model and does not include social-page downloading, speaker diarization, or word-level timestamps.