transcribe — Claude Code skill: what it does, how to install
Transcribes audio recordings into text and identifies speakers using OpenAI models. Helpful when processing interviews and team meetings.
npx claude-code-templates@latest --skill media/transcribeWhat transcribe 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.
What it helps with
- 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 for the agent
- Transcribe the audio file
interview.mp3and save the plain text output tointerview.txt - Run speaker diarization on
meeting.m4ausing voice samplesrefs/alice.wavandrefs/bob.wav - Convert
voice.wavinto text using the fast default model
How to install transcribe
1claude-code-templates
npx claude-code-templates@latest --skill media/transcribe2Skills CLI (Vercel)
npx skills add davila7/claude-code-templates --skill transcribe -a claude-code3Manually: put the files in place
~/.claude/skills/transcribe/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/transcribe/
Manually: put the files in place
.agents/skills/transcribe/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/transcribe/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install davila7/claude-code-templates transcribe2Manually: put the files in place
.github/skills/transcribe/SKILL.mdPlatform CLI
gemini skills install https://github.com/davila7/claude-code-templates --path cli-tool/components/skills/media/transcribeManually: put the files in place
.devin/skills/transcribe/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about transcribe
How to install transcribe in Claude Code?
Run npx claude-code-templates@latest --skill media/transcribe in your terminal. This configures the skill for Claude Code.
What does transcribe do?
It triggers a Python CLI tool that passes audio files to OpenAI transcription models, outputting plain text or diarized JSON.
What dependencies are required?
You need Python 3, the openai package installed via uv pip install openai or pip, and an exported OPENAI_API_KEY.