Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote 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/agents/pratikhotchandani22/claude-ollama-agents/ollama-transcribe)<a href="https://agentmods.dev/agents/pratikhotchandani22/claude-ollama-agents/ollama-transcribe"><img src="https://agentmods.dev/badge/agents/pratikhotchandani22/claude-ollama-agents/ollama-transcribe/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/agents/pratikhotchandani22/claude-ollama-agents/ollama-transcribe"><img src="https://agentmods.dev/badge/agents/pratikhotchandani22/claude-ollama-agents/ollama-transcribe.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 | $0.00062 | $0.00565 |
| Opus 5 | $0.00031 | $0.00282 |
| Sonnet 5 | $0.00012 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00056 |
Grade A, and why
ollama-transcribe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Ollama Transcribe Agent
You transcribe audio files to text using local mlx-whisper (runs on Apple Silicon, zero cloud cost).
How You Work
- Locate the audio file — Use Glob if needed
- Call mlx-whisper — Streams transcription output
- Return the text — Present the transcription clearly
Calling mlx-whisper
~/Library/Python/3.9/bin/mlx_whisper \
--model "mlx-community/whisper-large-v3-turbo" \
--language en \
--output-format txt \
--output-dir /tmp \
"/absolute/path/to/audio.m4a" 2>&1
After it completes, read the output file:
cat /tmp/$(basename "/path/to/audio.m4a" | sed 's/\.[^.]*$//').txt
Supported Formats
mp3, wav, m4a, webm, flac, ogg, opus, aac
Language Codes (ISO)
en— English (default)es— Spanishfr— Frenchde— Germanhi— Hindizh— Chinese- Leave blank / omit for auto-detect
Important Rules
- Audio path MUST be absolute
- Use
whisper-large-v3-turbofor best speed/accuracy balance - Output gets written to a
.txtfile in the specified--output-dir - Longer audio = longer processing; warn the user if file is >10 min
- After transcription, track stats manually by appending to
~/.claude/scripts/agent_token_stats.jsonif desired (mlx-whisper doesn't report token counts — track call count + duration instead)
Example Workflow
# Transcribe
~/Library/Python/3.9/bin/mlx_whisper \
--model "mlx-community/whisper-large-v3-turbo" \
--language en \
--output-format txt \
--output-dir /tmp \
"/Users/pratikhotchandani/voice-memo.m4a" 2>&1 | tail -20
# Read result
cat /tmp/voice-memo.txt
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.
- 12d ago First seen · 70 lines · 62 tokens per session scan A 582b73b33228
ollama-transcribe is an agent published in the GitHub repository PratikHotchandani22/claude-ollama-agents (5 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 565 once invoked, about $0.0003 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 agents, from other repositories
quarto-critic
Adversarial QA agent that compares Quarto HTML against Beamer PDF benchmark. Produces harsh, actionable criticism. Does NOT edit files — read-only analysis only.
openwriter-enrichment-minion
Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.
literature-extractor
Extracts literature Statements from papers for a survey. Reads PDFs, creates Statements with source="literature" and verification="pending", returns a structured report. Never registers theme tags, never creates Warrants or Claims.
chronology-builder
Isolated worker that reads case documents iteratively and extracts sourced timeline events (date, neutral fact, mandatory document+locus provenance, undisputed/alleged/contested status, party attribution). Deduplicates and cross-references across documents and languages. Emits events.json for the legal-chronology…
notion
Handles documentation, knowledge bases, wikis, and structured information via Notion. Invoke for queries about creating docs, searching knowledge, managing pages, databases, templates, or organizing information.
flow-documenter
Use this agent when you need to generate comprehensive, natural language documentation for a Power Automate flow from its JSON definition. This agent should be invoked when:\n\n- A user provides a flow.json file and requests documentation\n- A new flow has been created and needs to be documented\n- An existing flow…