# speech-to-text

speech-to-text converts audio and video files to text with automatic language detection, timestamps, and speaker identification. Requires a Noiz API key.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 198 installs · ★ 539 repo stars
- Author: NoizAI
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/NoizAI/skills/tree/HEAD/skills/speech-to-text/SKILL.md
- Updated: 2026-09-28
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/noizai-speech-to-text

## What it does

The skill runs a Python script that uploads audio files to Noiz servers for processing. It handles files up to 50 MB and 10 minutes long in mp3, wav, m4a, ogg, flac, aac, and webm formats. By default it outputs plain text, but can return full JSON with segment breakdowns, timing information, and speaker labels.

You need the `requests` package (install via pip) and a Noiz API key to proceed. Save the key once through configuration or pass it as the `NOIZ_API_KEY` environment variable. Pricing is $0.0006 per audio second; a ten-minute file runs about $0.36.

The skill activates on commands like "transcribe", "get subtitles", "identify speakers" or "what does this audio say". It supports automatic multilingual detection and explicit language selection via the `--language` flag.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NoizAI/skills --skill speech-to-text -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/speech-to-text/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/speech-to-text/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NoizAI/skills --skill speech-to-text -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/speech-to-text/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NoizAI/skills --skill speech-to-text -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/speech-to-text/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NoizAI/skills skills/speech-to-text
```

2. **Manually: put the files in place**
- File: `.github/skills/speech-to-text/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NoizAI/skills --skill speech-to-text -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NoizAI/skills --path skills/speech-to-text
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/speech-to-text/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NoizAI/skills --skill speech-to-text -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/NoizAI/skills/tree/HEAD/skills/speech-to-text/SKILL.md

## When to use it
- transcribe a podcast or interview into searchable text
- generate subtitles with timings from a video recording
- separate and label speech by different speakers in audio
- recognize and convert speech in multiple languages
- export transcription as JSON with segment metadata

## Example prompts
- Transcribe `meeting.wav` and save the result to `transcript.txt`
- Get a transcript of `podcast.m4a` in Spanish with speaker labels output as JSON
- Convert `interview.mp3` to text with automatic language detection

## Similar
- [azure-speech-to-text](https://affpapa.org/en/nevibecode/skills/azure-speech-to-text.md) — skill · 913 installs
- [ASR](https://affpapa.org/en/nevibecode/skills/answerzhao-asr.md) — skill · 209 installs
- [text-to-speech](https://affpapa.org/en/nevibecode/skills/calesthio-text-to-speech.md) — skill · 1300 installs
- [Text to Speech — 20+ Languages, MP3 Output](https://affpapa.org/en/nevibecode/mcp/text-to-speech-20-languages-mp3-output.md) — MCP server · 2769 installs
- [azure-speech-to-text-rest-py](https://affpapa.org/en/nevibecode/skills/azure-speech-to-text-rest-py.md) — skill · 2 installs
- [multimodal-whisper](https://affpapa.org/en/nevibecode/skills/multimodal-whisper.md) — skill · 91 installs

## Other versions with the same name
- [speech-to-text · elevenlabs](https://affpapa.org/en/nevibecode/skills/speech-to-text.md) — 16200 installs
- [speech-to-text · martinholovsky](https://affpapa.org/en/nevibecode/skills/martinholovsky-speech-to-text.md) — 284 installs
- [speech-to-text · 101-skills](https://affpapa.org/en/nevibecode/skills/101-skills-speech-to-text.md) — 242 installs

From the same set: [noizai/skills](https://affpapa.org/en/nevibecode/by/noizai/skills.md) — 7 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
