soliloquy-tts 0.5.0

A text-to-speech MCP server powered by Kokoro — gives Claude Code a voice

Soliloquy

A text-to-speech MCP server powered by Kokoro — gives Claude Code a voice.

One command to install. No config, no API keys, no setup.

Requirements

• macOS, Windows, or Linux
• Python 3.10+
• PortAudio (audio output library)

Platform	PortAudio Install
macOS	brew install portaudio
Windows	Bundled with sounddevice (no action needed)
Linux	sudo apt install libportaudio2

Note: Installation downloads ~2GB of dependencies (PyTorch, model weights). First run also downloads the Kokoro-82M model from HuggingFace.

Quick Start

No install needed (requires uv):

# Install uv if you don't have it:
# macOS:   brew install uv
# Windows: powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

claude mcp add soliloquy -s user -- uvx soliloquy-tts

Or with pip:

pip install soliloquy-tts
claude mcp add soliloquy -s user -- soliloquy

Restart Claude Code after registering. Claude can now speak.

Scope: -s user registers Soliloquy globally so it's available in every project. Use -s local (or omit the flag) to register it for the current project only.

How It Works

Soliloquy uses a hybrid architecture to share a single model across multiple Claude Code sessions:

• First session loads the Kokoro model and starts a local backend server
• Additional sessions detect the running backend and connect as lightweight proxies (near-instant startup, no extra memory)
• If the backend exits, the next session automatically takes over

This is completely transparent — no configuration needed.

Why Soliloquy?

	Cloud TTS (ElevenLabs, OpenAI, etc.)	Soliloquy
Privacy	Text sent to cloud	Nothing leaves your machine
Cost	$0.18–15/1M chars	Free forever
Offline	No	Yes
Usage Limits	Quotas / rate limits	Unlimited
Latency	200–500ms (network)	~50–100ms (local)
AI Integration	Developer calls API from code	AI agent decides when to speak
Setup	API keys + billing	One command, no config

Tools

speak

Synthesize and play text aloud.

Parameter	Default	Description
text	(required)	Text to speak
voice	af_heart	Voice ID (see below)
speed	1.0	Speed multiplier (0.5 - 2.0)
lang	en-us	Language code

read_aloud

Read a file aloud directly — Claude just passes the file path, no need to process the content first. Supports plain text and markdown.

Parameter	Default	Description
path	(required)	Path to the file to read
voice	af_heart	Voice ID (see below)
speed	1.0	Speed multiplier (0.5 - 2.0)
lang	en-us	Language code

list_voices

Returns all available voices with language and gender metadata.

Voices

28 voices across American and British English:

Voice	Accent	Gender
af_heart	American	Female
af_alloy	American	Female
af_aoede	American	Female
af_bella	American	Female
af_jessica	American	Female
af_kore	American	Female
af_nicole	American	Female
af_nova	American	Female
af_river	American	Female
af_sarah	American	Female
af_sky	American	Female
am_adam	American	Male
am_echo	American	Male
am_eric	American	Male
am_fenrir	American	Male
am_liam	American	Male
am_michael	American	Male
am_onyx	American	Male
am_puck	American	Male
am_santa	American	Male
bf_alice	British	Female
bf_emma	British	Female
bf_isabella	British	Female
bf_lily	British	Female
bm_daniel	British	Male
bm_fable	British	Male
bm_george	British	Male
bm_lewis	British	Male

Languages

en-us (default), en-gb, ja, zh, es, fr, hi, it, pt-br

Uninstall / Update

To unregister from Claude Code:

claude mcp remove soliloquy -s user

If using uvx, clear the cache to force a fresh download on next run:

uv cache clean soliloquy-tts

If using pip:

pip uninstall soliloquy-tts

Development

git clone https://github.com/bstovall/soliloquy.git
cd soliloquy
python3.11 -m venv .venv
source .venv/bin/activate
pip install -e .

Run the benchmark:

python scripts/benchmark_tts.py

License

MIT