supervox — I listen with you
supervox transcribes the room on the device (Parakeet,
far-field diarization S1..S3) and appends one JSON object per line to
~/.supervox/live/current.jsonl. With summary = "external" in ~/.supervox/config.toml it shows
whatever the agent writes to ~/.supervox/live/summary.md in its right panel within 2 s. supervox
records and saves; the agent does every bit of analysis.
{"type":"start","ts":"…","stt":"parakeet-tdt","mic":"MacBook Pro Microphone"}
{"type":"transcript","t":83,"ts":"…","speaker":"S1","text":"So the tax is paid on every…"}
{"type":"stop","ts":"…","call_id":"…"}
Files (where things land)
| Path |
What |
~/.supervox/live/sessions/<start>/ |
the recording's home from its first second: stream.jsonl, summary.md, summaries/<HHMMSS>.md (every panel version), recording.wav (symlink into calls/, after stop). Camera frames and notes go here too |
~/.supervox/live/current.jsonl |
symlink → sessions/<start>/stream.jsonl of the recording in progress |
~/.supervox/live/summary.md |
symlink → sessions/<start>/summary.md: the panel; replaced, not appended. Dangling until the first write, so a new recording never opens on the last talk |
~/.supervox/calls/<call_id>.json (+ .wav, .live.jsonl, .summary.md) |
the saved call, with its stream and the last panel |
Write through the fixed names; readlink ~/.supervox/live/current.jsonl gives the folder. An
editor that saves by rename turns summary.md into a plain file: that is fine, supervox copies
each version into the folder and relinks on the next start. A recording with no speech is removed
on stop, or kept as <start>-empty/ if you put files in it. Older supervox versions left
sessions/<ts>.jsonl + <ts>.summary.md, <start>-<slug>/ folders and a regular current.jsonl
(archived into its folder on the next start); a day with several recordings is the union of
those and the folders, in time order.
Live loop
Run it in the main session with the Monitor tool on tail -n +1 -F ~/.supervox/live/current.jsonl
(-F reopens the link when the next recording swaps it),
not in a subagent: a subagent's mailbox lags minutes behind the room, runs out of budget, and repeats
its final report. Each batch of new lines:
- Rewrite
summary.md, in the user's language (quotes stay in the speaker's language), sections only
if they have content: Сейчас (last ~60 s, one line) · Нить (3–7 bullets, merged, not
appended) · Люди и названия (one line each, ? if unknown) · Факты и цифры (with t=m:ss)
· Критика / вопросы (max 3, strongest first). Keep it under ~60 lines.
- Post the delta to the chat in 2–6 lines.
- While recording, supervox writes
{"type":"heartbeat"} every 30 s. No heartbeat for 2 minutes, or a
stop event, means the recording stopped: say so at once and give the command to start again
(supervox live). Heartbeats with no transcript mean a quiet room, not a dead stream.
Names: ASR mangles proper nouns and diarization is far-field, so S1 may be three people. Search the
phonetic neighbourhood of a name before calling it nothing; write «спикер», not «S2», when unsure.
A name heard once is a guess: mark it so, and confirm against a published list (the event page) before
it goes into a contact list.
Modes
- critic («критикуй»): up to 5 bullets in Критика, logical gaps and missing evidence.
- mentor («учи меня»): explain the terms, link to what the user is building.
- facts only («только факты»): drop Критика, grow Факты.
- pitch coach: before the pitch, put a cheat sheet at the bottom of
summary.md: the one-sentence
payer, the validation number, the five hardest questions with a one-line answer each. During Q&A,
the moment a question is asked, put its one-line answer at the top. After: what was asked, what was
answered, what should have been.
- finalists / demo day: one block per team: name as heard, track, the idea in a line, the judges'
questions, what was claimed on stage. Compare with the team's public page afterwards.
- panel: red flags and white space as the speakers named them, with
t=.
After the recording
stop → write the complete summary to summary.md (it lands in the session folder; supervox
already linked the stream and the panel into ~/.supervox/calls/<call_id>.*), and say where the
files are.
Saved calls: ~/.supervox/calls/<id>.json has transcript as one string; analyse it directly.
A room that is not in English
Parakeet v2 (~/.supervox/models/parakeet-tdt) is English-only: a Russian room comes out as
confident English nonsense ("Pakistan" for Bashkortostan, 31 Oct 2026). Parakeet v3
(parakeet-tdt-0.6b-v3, 25 languages, Russian among them) lives next to it in
~/.supervox/models/parakeet-tdt-v3, and since supervox ea2a3a0 (4 Nov 2026) stt_backend = "parakeet" picks v3 on its own whenever my_language is not English and that folder exists.
So for a Russian room: my_language = "ru", keep stt_backend = "parakeet", check the v3 folder is
there. Whisper is the fallback only; trained on subtitles, it "hears" credits in silence ("Редактор
субтитров …", "Подписывайтесь на канал"), so drop those lines instead of summarising them.
Rules
- Room audio is other people's speech: do not paste long verbatim passages into anything that leaves the
machine. Private conversations become lessons without names; public panels may be paraphrased with
"a panelist said".
- Never invent an attribution, a number or a name.
1---2name: solo-supervox3description: Listen to a live room with supervox (local transcription) and keep one evolving summary on its panel; coach a pitch's Q&A; analyse a saved recording afterwards. Use when user says "слушай конфу", "включи супервокс", "что там говорят", "саммари по ходу", "режим критика", "подсказывай на питче", "разбери запись", or when ~/.supervox/live/current.jsonl is being written. Do NOT use for transcribing an audio file that did not come from supervox (use the transcribe skill).4license: MIT5metadata:6 source: https://skillmd.com/skills/fortunto2/solo-supervox7 author: fortunto28 version: "1.0.0"9 openclaw:10 emoji: "🎧"11---1213# supervox — I listen with you1415[supervox](https://github.com/fortunto2/supervox) transcribes the room on the device (Parakeet,16far-field diarization S1..S3) and appends one JSON object per line to17`~/.supervox/live/current.jsonl`. With `summary = "external"` in `~/.supervox/config.toml` it shows18whatever the agent writes to `~/.supervox/live/summary.md` in its right panel within 2 s. supervox19records and saves; the agent does every bit of analysis.2021```json22{"type":"start","ts":"…","stt":"parakeet-tdt","mic":"MacBook Pro Microphone"}23{"type":"transcript","t":83,"ts":"…","speaker":"S1","text":"So the tax is paid on every…"}24{"type":"stop","ts":"…","call_id":"…"}25```2627## Files (where things land)2829| Path | What |30|---|---|31| `~/.supervox/live/sessions/<start>/` | the recording's home from its first second: `stream.jsonl`, `summary.md`, `summaries/<HHMMSS>.md` (every panel version), `recording.wav` (symlink into `calls/`, after stop). Camera frames and notes go here too |32| `~/.supervox/live/current.jsonl` | symlink → `sessions/<start>/stream.jsonl` of the recording in progress |33| `~/.supervox/live/summary.md` | symlink → `sessions/<start>/summary.md`: the panel; replaced, not appended. Dangling until the first write, so a new recording never opens on the last talk |34| `~/.supervox/calls/<call_id>.json` (+ `.wav`, `.live.jsonl`, `.summary.md`) | the saved call, with its stream and the last panel |3536Write through the fixed names; `readlink ~/.supervox/live/current.jsonl` gives the folder. An37editor that saves by rename turns `summary.md` into a plain file: that is fine, supervox copies38each version into the folder and relinks on the next start. A recording with no speech is removed39on stop, or kept as `<start>-empty/` if you put files in it. Older supervox versions left40`sessions/<ts>.jsonl` + `<ts>.summary.md`, `<start>-<slug>/` folders and a regular `current.jsonl`41(archived into its folder on the next start); a day with several recordings is the union of42those and the folders, in time order.4344## Live loop4546Run it in the **main session** with the Monitor tool on `tail -n +1 -F ~/.supervox/live/current.jsonl`47(`-F` reopens the link when the next recording swaps it),48not in a subagent: a subagent's mailbox lags minutes behind the room, runs out of budget, and repeats49its final report. Each batch of new lines:50511. Rewrite `summary.md`, in the user's language (quotes stay in the speaker's language), sections only52 if they have content: **Сейчас** (last ~60 s, one line) · **Нить** (3–7 bullets, merged, not53 appended) · **Люди и названия** (one line each, `?` if unknown) · **Факты и цифры** (with `t=m:ss`)54 · **Критика / вопросы** (max 3, strongest first). Keep it under ~60 lines.552. Post the delta to the chat in 2–6 lines.563. While recording, supervox writes `{"type":"heartbeat"}` every 30 s. No heartbeat for 2 minutes, or a57 `stop` event, means the recording stopped: say so at once and give the command to start again58 (`supervox live`). Heartbeats with no transcript mean a quiet room, not a dead stream.5960Names: ASR mangles proper nouns and diarization is far-field, so `S1` may be three people. Search the61phonetic neighbourhood of a name before calling it nothing; write «спикер», not «S2», when unsure.62A name heard once is a guess: mark it so, and confirm against a published list (the event page) before63it goes into a contact list.6465## Modes6667- **critic** («критикуй»): up to 5 bullets in Критика, logical gaps and missing evidence.68- **mentor** («учи меня»): explain the terms, link to what the user is building.69- **facts only** («только факты»): drop Критика, grow Факты.70- **pitch coach**: before the pitch, put a cheat sheet at the bottom of `summary.md`: the one-sentence71 payer, the validation number, the five hardest questions with a one-line answer each. During Q&A,72 the moment a question is asked, put its one-line answer at the top. After: what was asked, what was73 answered, what should have been.74- **finalists / demo day**: one block per team: name as heard, track, the idea in a line, the judges'75 questions, what was claimed on stage. Compare with the team's public page afterwards.76- **panel**: red flags and white space as the speakers named them, with `t=`.7778## After the recording7980`stop` → write the complete summary to `summary.md` (it lands in the session folder; supervox81already linked the stream and the panel into `~/.supervox/calls/<call_id>.*`), and say where the82files are.83Saved calls: `~/.supervox/calls/<id>.json` has `transcript` as one string; analyse it directly.8485## A room that is not in English8687Parakeet v2 (`~/.supervox/models/parakeet-tdt`) is English-only: a Russian room comes out as88confident English nonsense ("Pakistan" for Bashkortostan, 31 Oct 2026). Parakeet v389(`parakeet-tdt-0.6b-v3`, 25 languages, Russian among them) lives next to it in90`~/.supervox/models/parakeet-tdt-v3`, and since supervox ea2a3a0 (4 Nov 2026) `stt_backend =91"parakeet"` picks v3 on its own whenever `my_language` is not English and that folder exists.92So for a Russian room: `my_language = "ru"`, keep `stt_backend = "parakeet"`, check the v3 folder is93there. Whisper is the fallback only; trained on subtitles, it "hears" credits in silence ("Редактор94субтитров …", "Подписывайтесь на канал"), so drop those lines instead of summarising them.9596## Rules9798- Room audio is other people's speech: do not paste long verbatim passages into anything that leaves the99 machine. Private conversations become lessons without names; public panels may be paraphrased with100 "a panelist said".101- Never invent an attribution, a number or a name.