ollama-transcribe

ollama-transcribe is an agent for Claude Code from PratikHotchandani22/claude-ollama-agents. It costs 62 tokens per session (565 once invoked), scanned A, original, MIT.

An audio-to-text agent that transcribes voice memos, meetings, podcasts, and other recordings using a speech-recognition model running on the local computer. It supports common audio formats such as MP3, WAV, M4A, and WebM.

In plain words
What is it for?
Use it to turn audio files into text, with automatic language detection or a specified language, and save the transcription as a text file.
Why use it?
It removes the need to type out recordings manually or send them to a cloud transcription service. Processing happens locally on supported Apple Silicon computers.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; reads .claude/ paths.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/pratikhotchandani/voice-memo.m4a.

Good fit Use it to turn audio files into text, with automatic language detection or a specified language, and save the transcription as a text file.

Compare 6 agents from other repositories ↓
Install

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.

Made for: Claude Code.

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.

agentmods badge for ollama-transcribe

README.md
[![agentmods](https://agentmods.dev/badge/agents/pratikhotchandani22/claude-ollama-agents/ollama-transcribe/github.svg)](https://agentmods.dev/agents/pratikhotchandani22/claude-ollama-agents/ollama-transcribe)
Your own site
<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.

agentmods 80×15 button for ollama-transcribe

Your own site · 80×15
<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>
Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 565 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 12d ago against content hash 582b73b33228, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

agents/ollama-transcribe.md · 70 lines

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

  1. Locate the audio file — Use Glob if needed
  2. Call mlx-whisper — Streams transcription output
  3. 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 — Spanish
  • fr — French
  • de — German
  • hi — Hindi
  • zh — Chinese
  • Leave blank / omit for auto-detect

Important Rules

  • Audio path MUST be absolute
  • Use whisper-large-v3-turbo for best speed/accuracy balance
  • Output gets written to a .txt file 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.json if 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
Changes

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.

  1. 12d ago First seen · 70 lines · 62 tokens per session scan A 582b73b33228

Subscribe to this mod's changes

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.

Related

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.

brycewang-stanford/Auto-Empirical-Research-Skills · 38 tokens

openwriter-enrichment-minion

Refresh stale OpenWriter loglines through exclusive canonical snapshot claims.

travsteward/openwriter · 19 tokens

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.

yqi96/warranted · 48 tokens

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…

fedec65/bettercallclaude · 103 tokens

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.

tomcounsell/ai · 42 tokens

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…

MacroMan5/AutomationHelper_plugins · 368 tokens