# Hume MCP Server

> Official Hume server for Octave TTS — emotionally expressive, acting-directed speech.

- **Category:** Voice & Dialogue
- **Vendor:** Hume AI (official)
- **Pricing:** freemium
- **Verified:** 2026-06-11

## What it does

Hume's official MCP server drives Octave, a speech-language model that 'performs' text rather than just pronouncing it, with prompt-directed emotion and delivery. Ideal for film dialogue and narration where acting nuance matters; agents can iterate on takes, save designed voices, and replay prior audio.

## Connect

- Claude Code: `claude mcp add hume -e HUME_API_KEY=YOUR_KEY -- npx @humeai/mcp-server`
- Local: `npx @humeai/mcp-server`

**Auth:** api_key (env `HUME_API_KEY`) — https://platform.hume.ai

## Capabilities

`tts` · `voice-design` · `expressive-performance` · `voice-library`

## Sample tools

`tts` · `play_previous_audio` · `list_voices` · `save_voice` · `delete_voice`

## Field notes

Official, published as @humeai/mcp-server on npm with first-party docs. Smaller tool surface than ElevenLabs/Cartesia (TTS-focused). Octave 2 multilingual model strengthens its case for character performance.

## Links

- Site: https://www.hume.ai
- Docs: https://dev.hume.ai/docs/text-to-speech-tts/mcp-server
- Repo: https://github.com/HumeAI/mcp-server-hume

---

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