
Live Transcribe
- 11 installs
- 44 repo stars
- Updated July 8, 2026
- aviz85/claude-skills-library
Live Transcribe is a Claude skill that starts real-time microphone transcription using ElevenLabs Scribe v2 Realtime.
About
Live Transcribe starts real-time microphone transcription using ElevenLabs Scribe v2 Realtime. A developer invokes it to capture dictation or speech live; the script streams audio over WebSocket and continuously writes committed text to a temp file. It checks whether a session is already running and reports the output file path and stop options.
- Starts real-time microphone transcription using ElevenLabs Scribe v2 Realtime
- Streams audio over WebSocket and writes committed text to a temp file continuously
- Plays Hebrew audio cues and supports voice or command stop
Live Transcribe by the numbers
- 11 all-time installs (skills.sh)
- Ranked #1,471 of 2,719 Automation & Workflows skills by installs in the Skillselion catalog
- Data as of Jul 28, 2026 (Skillselion catalog sync)
live-transcribe capabilities & compatibility
byo-api-key (ElevenLabs)
- Capabilities
- transcription · speech to text · dictation
- Use cases
- transcription
- Pricing
- Bring your own API key
What live-transcribe says it does
The script captures audio, streams to ElevenLabs Scribe v2 Realtime via WebSocket, and writes committed text to a temp file continuously.
Start real-time microphone transcription using ElevenLabs Scribe v2 Realtime.
Check if one is already running:
npx skills add https://github.com/aviz85/claude-skills-library --skill live-transcribeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 11 |
|---|---|
| repo stars | ★ 44 |
| Last updated | July 8, 2026 |
| Repository | aviz85/claude-skills-library ↗ |
What it does
Starting real-time microphone transcription that streams audio to ElevenLabs Scribe v2 and writes text continuously.
Who is it for?
Starting a live dictation or speech-capture session streamed to ElevenLabs Scribe.
Skip if: Reading or stopping a transcript (use live-transcribe-read or live-transcribe-stop).
When should I use this skill?
When the user wants to start live transcription, dictation, or real-time speech capture.
What you get
A running background process that streams mic audio to ElevenLabs and writes live transcript text to a temp file.
- a live transcript temp file
- a running transcription process
By the numbers
- reminder audio cue plays every 30 minutes
- waits ~4 seconds for the startup JSON
Files
Live Transcribe — Start
Start real-time microphone transcription. The script captures audio, streams to ElevenLabs Scribe v2 Realtime via WebSocket, and writes committed text to a temp file continuously.
Start command
source ~/.claude/skills/transcribe/scripts/.env && \
ELEVENLABS_API_KEY="$ELEVENLABS_API_KEY" \
nohup python3 ~/.claude/scripts/realtime-transcribe.py > /tmp/realtime-transcribe.log 2>&1 &Wait ~4 seconds, then read the first line of /tmp/realtime-transcribe.log for the startup JSON:
{"status": "started", "pid": 12345, "output_file": "/tmp/transcribe-20260526-143022.txt", ...}Before starting
Check if one is already running:
test -f /tmp/realtime-transcribe.pid && kill -0 $(cat /tmp/realtime-transcribe.pid) 2>/dev/null && echo "ALREADY RUNNING"If already running, tell the user and offer to stop first.
What to tell the user
1. Transcription is running 2. The output file path 3. Ways to stop: say "אוקי, זה מספיק, בוא נעצור את התמלול", or ask the agent to stop, or /live-transcribe-stop 4. They can ask to read the transcript anytime
Audio cues
Pre-recorded sounds play automatically:
- Start: "התחלתי תמלול!" (before recording begins)
- Stop: "סיימתי את התמלול." (after recording ends)
- Reminder: "אני עדיין מתמלל." (every 30 minutes)