Listen to a live room and keep one running summary (/solo-supervox)
With supervox transcribing locally, the agent keeps one evolving summary on screen during a talk or a call, coaches a pitch's Q&A, or analyses a saved recording afterwards.
/solo-supervox Listen to this room. Keep one summary of the talk in my language, rewritten as it goes, with the open questions and any numbers said out loud. At the end, list what I should follow up on and who said it.
In Claude Code, paste the prompt as a message, or run /supervox which does this end to end.
Install
npx skills add fortunto2/solo-factory --skill solo-supervox# or, as a Claude Code plugin (the command is then /solo:supervox):
claude plugin marketplace add https://github.com/fortunto2/solo-factory
claude plugin install solo@solo --scope userSteps
- Install supervox (github.com/fortunto2/supervox, a Rust voice toolkit) and the skill with the first line above. Start a new Claude Code session.
- Start a recording in supervox. It transcribes on the device and appends one JSON line per phrase, with speaker labels.
- Run the skill. It watches the live transcript and rewrites one summary file that supervox shows in its panel.
- After the recording, ask it to analyse the saved call.
Tips
- Nothing leaves the machine for transcription.
- The agent does all the analysis; supervox only records and saves.
- For an audio file that did not come from supervox, use the transcribe skill instead.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. |
| skill | npx skills add fortunto2/solo-factory --skill solo-supervox · source |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| source | supervox skill in solo-factory (MIT) |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-10 |
| for agents | skill-supervox.md |
Related
Transcribe audio and video locally with word timings (/solo-transcribe)
Transcribe audio or video to text locally: on the Apple GPU with mlx-whisper large-v3, or faster-whisper on CPU/CUDA: with the language decided per stretch of speech, .srt subtitles, word timings…
Turn an article or PRD into a social media pack (/solo-content-gen)
Turn an article or a PRD into a social pack: LinkedIn posts, short captions for Reels and TikTok, and a thread, with claims marked as sourced or not.
Recording to MIDI: pick the model by material, then check it
Three local transcription models fail in different directions. The skill picks one by what the material is, runs it, and checks the result before you trust it.
Beat times and downbeats from a song in Node, with life2film-engine
A short Node script that decodes a song with ffmpeg and prints BPM, beat times and downbeats on your machine, ready to place cuts on. No upload, no API key.
Scan a screen recording for leaked secrets before you post it (screenshield)
Before a demo, lecture or stream goes public, scan the video for API keys, personal data and QR phishing, and blur what it finds. On-device OCR, no LLM needed for the scan.
Cut a vertical reel to a song with real beats (/solo-music-reels-cut)
Footage plus a music track becomes a 1080x1920 reel: beats and phrases detected for real, cut density that follows verse and chorus, 14 ffmpeg effects, a flash on every downbeat.