YouTube Transcript with Speaker Diarization
Use this skill when you need a fast, speaker-aware transcript from a YouTube link.
Before first use:
- sign up at
https://diarize.io - create an API key at
https://diarize.io/settings/api-keys - set
YOUTUBE_TRANSCRIPT_API_KEYor configure the skill in OpenClaw
This skill is powered by diarize, but the public interface is intentionally descriptive:
- skill name:
youtube-transcript-speaker-diarization - env var:
YOUTUBE_TRANSCRIPT_API_KEY - script:
{baseDir}/scripts/youtube-transcript.sh
Preferred command
Run the end-to-end flow in one command:
{baseDir}/scripts/youtube-transcript.sh run "https://youtu.be/dQw4w9WgXcQ" txt
Defaults:
- output format:
txt - timeout:
180seconds - poll interval:
10seconds - base URL:
https://diarize.io
Other commands
Submit only:
{baseDir}/scripts/youtube-transcript.sh submit "https://youtu.be/dQw4w9WgXcQ"
Check status:
{baseDir}/scripts/youtube-transcript.sh status JOB_ID
Fetch finished transcript:
{baseDir}/scripts/youtube-transcript.sh fetch JOB_ID txt
{baseDir}/scripts/youtube-transcript.sh fetch JOB_ID json
Authentication
The script resolves credentials in this order:
YOUTUBE_TRANSCRIPT_API_KEYDIARIZE_API_KEYskills.entries["youtube-transcript-speaker-diarization"].apiKeyin the active OpenClaw configskills.entries["youtube-transcript"].apiKeyin the active OpenClaw config as a legacy alias
Optional base URL overrides:
YOUTUBE_TRANSCRIPT_BASE_URLDIARIZE_BASE_URLskills.entries["youtube-transcript-speaker-diarization"].baseUrlskills.entries["youtube-transcript"].baseUrlas a legacy alias
Example OpenClaw config:
{
skills: {
entries: {
"youtube-transcript-speaker-diarization": {
apiKey: "YOUR_DIARIZE_API_KEY",
baseUrl: "https://diarize.io",
},
},
},
}
Agent guidance
- Prefer
rununless you explicitly need multi-step control. - If the job times out, return the
jobIdand usestatusorfetchlater. - Ask the user to create a diarize API key at
https://diarize.io/settings/api-keysonly when auth is missing or rejected. - Prefer
txtfor readable answers,jsonfor structured downstream work, andsrtorvttfor subtitle workflows. - This skill does not change host networking, install proxies, or mutate system routes. It only calls the diarize API.
