Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Knuckles-Team/audio-transcriber --skill audio-transcriber-transcriptiongit clone --depth 1 https://github.com/Knuckles-Team/audio-transcriberWrote 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/knuckles-team/audio-transcriber/audio-transcriber-transcription)<a href="https://agentmods.dev/skills/knuckles-team/audio-transcriber/audio-transcriber-transcription"><img src="https://agentmods.dev/badge/skills/knuckles-team/audio-transcriber/audio-transcriber-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/knuckles-team/audio-transcriber/audio-transcriber-transcription"><img src="https://agentmods.dev/badge/skills/knuckles-team/audio-transcriber/audio-transcriber-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 | $0.00119 | $0.01062 |
| Opus 5 | $0.00060 | $0.00531 |
| Sonnet 5 | $0.00024 | $0.00212 |
| Haiku 4.5 | $0.00012 | $0.00106 |
Grade A, and why
audio-transcriber-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 11d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audio Transcription
Whisper transcription of audio/video via the audio-transcriber MCP server. The
server prefers faster-whisper (CTranslate2) and falls back to openai-whisper;
GPU is used automatically when available (float16), else CPU (int8).
When to use
- Transcribe a local audio/video file (
.wav,.mp3,.mp4,.flac, …) to text. - Record from the microphone for N seconds and transcribe.
- Translate foreign-language audio to English (
task='translate'). - Emit subtitle/caption files (
txt,srt,vtt,json).
When NOT to use
- Persisting the transcript / audio into the knowledge graph → use
audio-transcriber-knowledge-graph. - Fetching the media from a URL first → use the
media-downloaderpackage, then transcribe the downloaded file. - Real-time audio-to-audio interaction (PersonaPlex) — that is a separate CLI mode, not part of this tool surface.
Prerequisites & environment
Connect via the mcp-client skill against the audio-transcriber MCP server.
ffmpeg should be installed for broad input-format support.
| Variable | Required | Notes |
|---|---|---|
WHISPER_MODEL |
optional | Default model when the caller omits model (default base) |
TRANSCRIBE_DIRECTORY |
optional | Default directory for recordings/exports |
MCP_TOOL_MODE (condensed|verbose|both) selects the condensed surface vs. the
1:1 verbose tools.
Tools & actions
| Tool | Purpose |
|---|---|
transcribe_audio |
Transcribe a file or a microphone recording; optionally export captions |
Key parameters
audio_file— path to transcribe. Provide this or a positiverecord_seconds.record_seconds— seconds to capture from the mic (only when noaudio_file).model—tiny/base/small/medium/large/large-v3/distil-large-v3/turbo.language— pin (e.g.en) to skip auto-detection; omit to auto-detect.task—transcribe(default) ortranslate(to English).word_timestamps— set for word-level timing.export_formats— subset of["txt","srt","vtt","json"].backend— forcefaster-whisperoropenai-whisper(default: auto).
What ships with it
1 file 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.
- 11d ago First seen · 92 lines · 119 tokens per session scan A 4f5d62d26690
audio-transcriber-transcription is a skill published in the GitHub repository Knuckles-Team/audio-transcriber (2 stars, last pushed 13d ago), licensed MIT. It adds 119 tokens to every session and 1,062 once invoked, about $0.0006 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…
faster-whisper
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables 20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.
audio-transcription-pipeline
Build audio transcription pipelines with Whisper, Deepgram, and AssemblyAI including speaker diarization and real-time streaming. Activate on: transcription, speech-to-text, diarization, audio processing, meeting transcripts. NOT for: text-to-speech synthesis (voice-audio-engineer), music generation (ai-engineer).
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
openai-whisper
Local speech-to-text with the Whisper CLI (no API key).