# transcribe

Transcribes audio recordings into text and identifies speakers using OpenAI models. Helpful when processing interviews and team meetings.

- skill · `type=skill` · Claude Code · 272 installs
- Author: openai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/media/transcribe
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/transcribe

## What it does

The skill handles speech-to-text workflows through an included script named `transcribe_diarize.py`. Standard runs send recordings to `gpt-4o-mini-transcribe` to generate simple text files quickly. When multi-speaker tracking is needed, it switches to `gpt-4o-transcribe-diarize` to return structured JSON with segmented dialogs.

You can provide audio references for up to 4 known speakers to improve diarization accuracy. However, custom prompts are unavailable under the diarization model. Any clip exceeding roughly 30 seconds triggers automated chunking to prevent processing limits.

Executing these jobs requires Python 3 with the `openai` package and a valid `OPENAI_API_KEY`. The script halts immediately if the key is missing from your shell variables. Outputs land in `output/transcribe/` unless you pass a custom destination with `--out` or `--out-dir`.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --skill media/transcribe
```

2. **Skills CLI (Vercel)**
```bash
npx skills add davila7/claude-code-templates --skill transcribe -a claude-code
```

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

### Codex

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

### Cursor

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install davila7/claude-code-templates transcribe
```

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

### Gemini CLI

**Platform CLI**
```bash
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/media/transcribe
```

### Windsurf (Devin Desktop)

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

### 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/davila7/claude-code-templates/tree/HEAD/cli-tool/components/skills/media/transcribe

## When to use it
- transcribe speech from an audio recording into plain text
- separate speaker turns across an interview recording
- match participants against sample reference audio
- export structured diarized dialogue to JSON

## Example prompts
- Transcribe the audio file `interview.mp3` and save the plain text output to `interview.txt`
- Run speaker diarization on `meeting.m4a` using voice samples `refs/alice.wav` and `refs/bob.wav`
- Convert `voice.wav` into text using the fast default model

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 350300 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 804 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