# Sanzaru (Whisper MCP)

> OpenAI Whisper/GPT-4o transcription, audio chat, and TTS in one local MCP server.

- **Category:** Transcription & Captions
- **Vendor:** Community (TJC-LP) (community)
- **Pricing:** paid
- **Verified:** 2026-06-11

## What it does

Community MCP server wrapping OpenAI's audio APIs: Whisper and GPT-4o transcription with enhancement templates, interactive 'chat with audio' analysis, format conversion/compression, and OpenAI TTS. A filmmaker-agent can transcribe and interrogate dailies, then generate scratch narration, all against a single OpenAI key.

## Connect

- Claude Code: `claude mcp add sanzaru -e OPENAI_API_KEY=YOUR_KEY -e SANZARU_MEDIA_PATH=/absolute/path/to/media -- uvx "sanzaru[all]"`
- Local: `uvx "sanzaru[all]"`

**Auth:** api_key (env `OPENAI_API_KEY`) — https://platform.openai.com (API keys)

## Capabilities

`transcription` · `audio-analysis` · `tts` · `format-conversion`

## Sample tools

`transcribe_audio` · `transcribe_with_enhancement` · `chat_with_audio` · `create_audio` · `convert_audio` · `compress_audio`

## Field notes

Successor to the widely-listed (now deprecated) arcaputo3/mcp-server-whisper. v0.6.2, Apr 2026, MIT. For fully local/offline transcription: jwulff/whisper-mcp and SmartLittleApps/local-stt-mcp (whisper.cpp, Apple Silicon, diarization).

## Links

- Repo: https://github.com/TJC-LP/sanzaru

---

Structured data: https://mcp.film/api/mcps/sanzaru.json · Directory: https://mcp.film