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 agentmods add commands/steipete/summarize/transcribergit clone --depth 1 https://github.com/steipete/summarizeWhat 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 | $0.00000 | $0.00608 |
| Opus 5 | $0.00000 | $0.00304 |
| Sonnet 5 | $0.00000 | $0.00122 |
| Haiku 4.5 | $0.00000 | $0.00061 |
Grade A, and why
transcriber 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 2d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
summarize transcriber
summarize transcriber setup [--model parakeet|canary] [--theme <name>]
Configures local ONNX transcription. The command prints the env vars you need to export — it doesn't write to your shell config. Once those vars are exported, --transcriber auto (or SUMMARIZE_TRANSCRIBER=auto) uses ONNX after Groq and before whisper.cpp and the remaining cloud fallbacks.
How auto picks a transcriber
When --transcriber auto is set (default), summarize tries providers in this order:
- Groq — fastest cloud option. Needs
GROQ_API_KEY. - Local ONNX (Parakeet or Canary), then
whisper.cpp— fully offline. ONNX needs the env vars from this command. - AssemblyAI / Gemini / OpenAI / FAL / Deepgram — cloud fallbacks, in that order, gated by their respective API keys.
OPENAI_WHISPER_BASE_URL changes the endpoint used by the OpenAI transcription stage; it is not a separate provider in the order above.
Subcommand
summarize transcriber setup
--model <name>
: parakeet (default) or canary. Picks which ONNX model the printed snippet targets.
--theme <name>
: CLI theme override.
The output is a labelled, copy-pasteable block of export lines for your shell. Re-run with the other model to switch.
Environment
Set by the printed snippet:
SUMMARIZE_ONNX_PARAKEET_CMD
: Command to run Parakeet ONNX transcription. Use {input} as the audio-file placeholder.
SUMMARIZE_ONNX_CANARY_CMD
: Command to run Canary ONNX transcription. Use {input} as the audio-file placeholder.
SUMMARIZE_TRANSCRIBER
: Optional. Select the local stage with auto, whisper, parakeet, or canary without passing --transcriber every time.
Examples
# Default: Parakeet.
summarize transcriber setup
# Set up Canary instead.
summarize transcriber setup --model canary
# After exporting the printed vars:
summarize "https://podcasts.apple.com/.../episode-..." --transcriber parakeet
See also
- ONNX transcription — how to actually install the model + runtime.
- Transcript provider flow — full selection waterfall.
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.
- 2d ago First seen · 68 lines · 0 tokens per session scan A 6c0353ccf4df
transcriber is a command published in the GitHub repository steipete/summarize (6,588 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 608 tokens. 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 2026-08-30.
Other commands, from other repositories
brand-generate
Generate an on-brand document from a saved Brand Profile.
stt
Transcribe a local audio file or remote audio URL into text.
audition-voices
Generate voice audition samples for a character using Venice TTS.
search
Search videos by text, image, or entity using TwelveLabs.
love
Love the current track — strong positive signal for this vibe.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.