speech-to-text
Transcribe audio and video to text using Whisper and ElevenLabs models with support for 99+ languages and diarization.
Install
npx skills add https://github.com/inferen-sh/skills --skill speech-to-textStats
| Total installs | 7,829 |
| Weekly installs | 7.8K |
| GitHub stars | 235 |
| First seen | Mar 12, 2026 |
| Source | @inferen-sh/skills |
Summary
- Three model options: ElevenLabs Scribe v2 (98%+ accuracy with diarization), Fast Whisper V3, and Whisper V3 Large for varying speed/accuracy tradeoffs
- Supports 99+ languages, optional timestamps, speaker diarization, and translation to English
- Common workflows include meeting transcription, podcast transcripts, video subtitles, and voice note conversion
- Requires inference.sh CLI (infsh) installation and authentication; accepts audio URLs or extracted video audio as input
Tags
Related skills
| Skill | Installs | vs speech-to-text |
|---|---|---|
| landing-page-design | 8,004 | +175 |
| firecrawl-crawl | 8,324 | +495 |
| agentic-principles | 7,552 | -277 |
| make-skill-template | 7,839 | +10 |
| agentic-eval | 7,961 | +132 |
FAQ
- How many installs does speech-to-text have?
- speech-to-text has 7,829 total installs and 7.8K installs this week.
- Where is speech-to-text hosted?
- speech-to-text is published by @inferen-sh/skills at https://github.com/inferen-sh/skills.
- How many GitHub stars does speech-to-text have?
- speech-to-text has 235 GitHub stars.
- When was speech-to-text first indexed?
- OrangeBot.AI first indexed speech-to-text on Mar 12, 2026.
- How do I install speech-to-text?
- Run: npx skills add https://github.com/inferen-sh/skills --skill speech-to-text