# openrouter-stt

openrouter-stt converts audio recordings into text using OpenRouter's speech-to-text API across models like Whisper and Chirp.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 319 installs · ★ 327 repo stars
- Author: OpenRouterTeam
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/OpenRouterTeam/skills/tree/HEAD/skills/openrouter-stt/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/openrouter-stt

## What it does

This skill instructs coding assistants how to query `POST /api/v1/audio/transcriptions`. It turns audio files into base64 payloads inside a standard JSON body and handles network requests using `curl`, TypeScript `fetch`, or Python `requests`. The API delivers the transcribed text along with billing details.

This endpoint is completely incompatible with OpenAI SDK conventions: sending `multipart/form-data` with a file attachment fails immediately. You must export an `OPENROUTER_API_KEY` environment variable before sending any transcription request.

The `input_audio.format` value must mirror the underlying audio encoding, whether `wav`, `mp3`, `flac`, `m4a`, `ogg`, `webm`, or `aac`. Mismatched containers cause mis-decoded transcripts or 400 validation failures.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add OpenRouterTeam/skills --skill openrouter-stt -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add OpenRouterTeam/skills --skill openrouter-stt -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add OpenRouterTeam/skills --skill openrouter-stt -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install OpenRouterTeam/skills skills/openrouter-stt
```

2. **Manually: put the files in place**
- File: `.github/skills/openrouter-stt/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add OpenRouterTeam/skills --skill openrouter-stt -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/OpenRouterTeam/skills --path skills/openrouter-stt
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add OpenRouterTeam/skills --skill openrouter-stt -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/OpenRouterTeam/skills/tree/HEAD/skills/openrouter-stt/SKILL.md

## When to use it
- convert recorded meetings and audio files into plain text
- generate captions from extracted video audio tracks
- query OpenRouter models supporting transcription modality
- pass vocabulary prompts to specific transcription providers

## Example prompts
- Transcribe meeting.wav using google/chirp-3 via OpenRouter
- Extract text from interview.mp3 using openai/whisper-large-v3
- List all available transcription models on OpenRouter

## Similar
- [9routerx-stt](https://affpapa.org/en/nevibecode/skills/9routerx-stt.md) — skill · ★ 259 repo stars
- [deepgram-speech](https://affpapa.org/en/nevibecode/skills/deepgram-speech.md) — skill · 132 installs
- [elevenlabs-stt](https://affpapa.org/en/nevibecode/skills/elevenlabs-stt.md) — skill · 236 installs
- [venice-audio-transcription](https://affpapa.org/en/nevibecode/skills/venice-audio-transcription.md) — skill · ★ 176 repo stars
- [agency-voice-ai-integration-engineer](https://affpapa.org/en/nevibecode/skills/agency-voice-ai-integration-engineer.md) — skill · ★ 85 repo stars
- [openai-whisper](https://affpapa.org/en/nevibecode/skills/openai-whisper.md) — skill · 7400 installs

From the same set: [openrouterteam/skills](https://affpapa.org/en/nevibecode/by/openrouterteam/skills.md) — 16 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
