What is whisper-speech-to-text CLAUDE.md?

Project instructions for a Python application that turns audio into written transcripts and labels different speakers. It uses Apple-optimized Whisper for transcription and pyannote for identifying who spoke when.

Working on audio transcription, speaker identification, timestamped transcripts, and plain-text, subtitle, or JSON output in this project.

It gives an agent the project’s structure, data flow, tools, and expected output formats so it can work consistently on the codebase.

How Vadiml1024/whisper-speech-to-text configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Vadiml1024/whisper-speech-to-text. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Vadiml1024/whisper-speech-to-text/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Vadiml1024/whisper-speech-to-text

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/vadiml1024/whisper-speech-to-text/claude-md/github.svg)](https://agentmods.dev/instructions/vadiml1024/whisper-speech-to-text/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/vadiml1024/whisper-speech-to-text/claude-md"><img src="https://agentmods.dev/badge/instructions/vadiml1024/whisper-speech-to-text/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/vadiml1024/whisper-speech-to-text/claude-md"><img src="https://agentmods.dev/badge/instructions/vadiml1024/whisper-speech-to-text/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 993 This file is loaded in full into every session.

When invoked 993 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00993	$0.00993
Opus 5.5	$0.00397	$0.00397
Sonnet 5.5	$0.00199	$0.00199
Haiku 4.5	$0.00099	$0.00099

Measured 2mo ago against content hash 34038506a57c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

whisper-speech-to-text CLAUDE.md 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 2mo 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.

CLAUDE.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Whisper Speech-to-Text with Speaker Diarization

Project Overview

This is a Python-based audio transcription project that combines MLX Whisper for speech-to-text with pyannote for speaker diarization. The project creates transcripts that identify different speakers in audio files.

Architecture

Core Components

speech-to-text.py - Main production script that combines MLX Whisper transcription with pyannote speaker diarization
test-mlx.py - Testing script for validating MLX Whisper API functionality
.env - Environment configuration file containing HuggingFace token

Technology Stack

Python 3 - Core runtime
mlx_whisper - Apple MLX-optimized Whisper for fast speech transcription on Apple Silicon
pyannote.audio - Speaker diarization pipeline from HuggingFace
HuggingFace Hub - Model hosting and authentication

Data Flow

Audio file input
MLX Whisper transcription (segments with timestamps)
Pyannote speaker diarization (speaker segments with timestamps)
Overlap analysis to assign speakers to transcript segments
Output formatting (txt, srt, or json)

Key Features

Multi-format output: Support for plain text, SRT subtitles, and JSON
Speaker identification: Assigns speaker labels to transcript segments
Timestamp alignment: Matches speakers to text based on time overlap
Error handling: Graceful handling of API failures and file issues

Dependencies

The project requires these key Python packages:

mlx_whisper - MLX-optimized Whisper implementation
pyannote.audio - Speaker diarization toolkit
Standard library: json, sys, os

Configuration

Environment Variables

HF_TOKEN - HuggingFace authentication token (stored in .env)
- Required for accessing pyannote speaker diarization models
- Format: hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Models Used

MLX Whisper: Default model or mlx-community/whisper-large-v3-mlx
Pyannote: pyannote/speaker-diarization-3.1

Read the full file on GitHub · 134 lines

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.

2mo ago First seen · 134 lines · 993 tokens per session scan A 34038506a57c

Subscribe to this mod's changes

whisper-speech-to-text CLAUDE.md is an instructions file published in the GitHub repository Vadiml1024/whisper-speech-to-text (11 stars, last pushed 1y ago), licensed MIT. It adds 993 tokens to every session, about $0.0040 per session on Opus 5.5. 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.

Data and AI Languages Python

whisper-speech-to-text CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
whisper-speech-to-text CLAUDE.mdVadiml1024/whisper-speech-to-text	Instructions file	11	1y ago	MIT	A	993	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

whisper-speech-to-text: Instructions file for Claude Code