Borrowing it
Nothing to install: this file belongs to chicogong/ffvoice-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/chicogong/ffvoice-engine/master/.claude/skills/ffvoice-transcription/SKILL.mdgit clone --depth 1 https://github.com/chicogong/ffvoice-engineWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/chicogong/ffvoice-engine/ffvoice-transcription)<a href="https://agentmods.dev/skills/chicogong/ffvoice-engine/ffvoice-transcription"><img src="https://agentmods.dev/badge/skills/chicogong/ffvoice-engine/ffvoice-transcription/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/chicogong/ffvoice-engine/ffvoice-transcription"><img src="https://agentmods.dev/badge/skills/chicogong/ffvoice-engine/ffvoice-transcription.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00078 | $0.01065 |
| Opus 5 | $0.00039 | $0.00532 |
| Sonnet 5 | $0.00016 | $0.00213 |
| Haiku 4.5 | $0.00008 | $0.00106 |
Grade A, and why
ffvoice-transcription scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ffvoice — offline speech transcription & diarization
ffvoice is an offline speech toolkit: speech-to-text (Whisper), speaker
diarization ("who spoke when"), and live captioning. Everything runs
locally — no audio leaves the machine, no API key.
Preconditions
Check ffvoice is installed: pip show ffvoice.
- Not installed →
pip install 'ffvoice[mcp]'. For speaker diarization add the extra:pip install 'ffvoice[mcp,diarization]'. - Models (Whisper weights, diarization models) download automatically to
~/.cache/ffvoice/on first use — no manual setup. The first run of a given model is slower while it downloads.
Two ways to use it — pick one
- MCP server — if an
ffvoiceMCP server is connected (tools namedtranscribe_file,list_audio_devices, etc. are available), call those tools directly. Preferred path for agent use. - CLI — otherwise drive the
ffvoicecommand-line tool. Works for batch/scripted use without an MCP connection.
MCP tools (when the ffvoice MCP server is connected)
| Tool | Use it for |
|---|---|
transcribe_file |
Transcribe one audio file → text + timestamped segments. Supports language, model size, word timestamps. |
transcribe_file_with_diarization |
Transcribe and label speakers — every segment gets a speaker_id. Use when the user asks "who said what". |
capture_and_transcribe |
Record from a microphone for N seconds and transcribe it. |
capture_and_caption |
Live streaming captions from the microphone (partial + final events). |
list_audio_devices |
Enumerate audio input devices. Call this FIRST whenever a microphone task needs a device index. |
Workflow:
- File transcription → confirm the path exists, then
transcribe_file(ortranscribe_file_with_diarizationwhen the user wants speakers). - Microphone →
list_audio_devicesfirst, thencapture_and_transcribeorcapture_and_captionwith the chosen device.
CLI usage (ffvoice command)
The CLI uses flag-style options (not subcommands). Confirm with
ffvoice --help. Common forms:
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 94 lines · 78 tokens per session scan A 7d65ad9efcc5
ffvoice-transcription is a skill published in the GitHub repository chicogong/ffvoice-engine (3 stars, last pushed 3mo ago), licensed MIT. It adds 78 tokens to every session and 1,065 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…
audio-transcriber-transcription
Speech-to-text on the audio-transcriber MCP server — run Whisper (faster-whisper, falling back to openai-whisper) over a local audio/video file or a microphone recording, and export txt/srt/vtt/json captions. Use when the agent must transcribe or translate spoken audio, generate subtitle/caption files, or pick a…
dialogue-transcriber
Transcribe audio or video of conversations — interviews, panel discussions, meetings, podcasts, YouTube videos — and identify who said what (speaker diarization) using the transcriber CLI. Use this skill whenever the user wants a transcript of multi-speaker audio, asks "who said what", wants speakers labeled or…