speech-to-text
speech-to-text is an agent skill published by deepgram. It lives in the deepgram/skills repository, which has 26 GitHub stars; we last read it on 2026-10-08.
This software connects to Deepgram for speech-to-text transcription, including live transcription and captions. It requires no specific credentials and can be used for general transcription or conversational audio with turn detection.
Install
skills is a generic installer for any repository of Claude agent skills -- it reads deepgram/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.
npx skills add deepgram/skills
What it connects to
Unverified means a mention in the skill’s own description, not a citation. A wrong claim here costs nothing to correct and nothing to trust yet.
Maintenance
Start here for Deepgram speech-to-text. Use when a task says "speech to text", "STT", "transcribe", "transcription", "live transcription", "captions", "diarization", "nova-3", "Flux", "turn detection", or "end of turn". Picks the model family (Nova on /v1/listen for general transcription, Flux STT on /v2/listen for conversational audio with built-in turn detection), gets a first request working, and routes to the api, docs, recipes, starters, examples, and per-language SDK skills for everything else.
Common questions about speech-to-text
- What does speech-to-text do?
- This software connects to Deepgram for speech-to-text transcription, including live transcription and captions. It requires no specific credentials and can be used for general transcription or conversational audio with turn detection.
- How do I install speech-to-text?
- Run npx skills add deepgram/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
- Who publishes speech-to-text?
- deepgram.
- Is speech-to-text maintained, and what licence does it use?
- Its repository has 26 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-02. We did not find a declared licence, so check the repository before you rely on it.