SpeechLab MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SpeechLab MCP Synthesize 'Welcome to SpeechLab!' as a WAV with Piper."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SpeechLab MCP
HappyMonkeyAI text-to-speech lab for agents, games, and video studios.
SpeechLab exposes an MCP server that can synthesize speech through local engines (Piper, Pocket TTS, Underdog Woof) and optionally Cartesia cloud voices. Clips are written as WAV files on disk; tools return absolute paths so an agent can copy them into a game or video project.
Copyright © 2026 Stephen Phillips / HappyMonkeyAI. Released under the MIT License.
Providers
Provider | Kind | Notes |
piper | local | Piper HTTP ( |
local | Pocket TTS ( | |
woof | local | Underdog Woof ( |
cartesia | cloud | Cartesia Sonic (requires |
Miso GPU quality is planned as a later Compose profile.
Related MCP server: narration-mcp
MCP tools
Tool | Purpose |
| Configured engines + health |
| Detailed health for one or all |
| Voice ids per provider |
|
|
Security
Copy
.env.example→.envlocally. Never commit.env.Leave
CARTESIA_API_KEYempty unless you need cloud TTS.Compose publishes MCP/TTS ports on loopback (
127.0.0.1) by default.Generated WAVs under
data/out/are gitignored.
Quick start (local stdio)
git clone https://github.com/HappyMonkeyAI/speech-lab-mcp.git
cd speech-lab-mcp
python -m venv .venv
# Windows PowerShell
.\.venv\Scripts\Activate.ps1
# macOS / Linux
# source .venv/bin/activate
pip install -e ".[dev]"
cp .env.example .env # Windows: copy .env.example .envPoint provider URLs in .env at running engines, or start Compose (below), then:
speech-lab-mcp --transport stdioCursor mcp.json example
{
"mcpServers": {
"speech-lab": {
"command": "speech-lab-mcp",
"args": ["--transport", "stdio"],
"env": {
"SPEECH_LAB_OUTPUT_DIR": "/absolute/path/to/speech-lab-mcp/data/out",
"SPEECH_LAB_PIPER_URL": "http://127.0.0.1:8090",
"SPEECH_LAB_POCKET_URL": "http://127.0.0.1:8091",
"CARTESIA_API_KEY": "",
"CARTESIA_VOICE_ID": ""
}
}
}
}On Windows, command can be the full path to .venv\\Scripts\\speech-lab-mcp.exe.
Docker Compose
MCP only (Cartesia works if a key is set in the environment; local engines optional):
docker compose up --build mcpStreamable HTTP endpoint: http://127.0.0.1:8765/mcp
Local Piper + Pocket:
docker compose --profile local up --buildProfiles:
Profile | Services |
(default) |
|
| Piper TTS |
| Pocket TTS |
| Piper + Pocket |
| Underdog Woof (set |
Build contexts default to sibling checkouts:
Piper →
../text-echo/ttsPocket →
../../miso/pocketWoof →
../agent-voice-tts/sidecars/woof-tts
Override with PIPER_BUILD_CONTEXT, POCKET_BUILD_CONTEXT, WOOF_BUILD_CONTEXT.
WAVs are written to ./data/out on the host.
Transports
Transport | Use |
| Cursor / local agent subprocess |
| Compose / remote clients ( |
| Legacy only — prefer streamable-http |
Typical agent flow
list_providers/provider_status— confirm a healthy engine.list_voices— pick a stable voice id per character.synthesize— generate a WAV; copy the returned path into your project assets.Keep a roster file in the consumer project so the same character always uses the same provider + voice.
Development
pip install -e ".[dev]"
pytestAttribution
Author: Stephen Phillips
Organization: HappyMonkeyAI
License: MIT
Third-party engines remain under their own licenses (Piper voices, Pocket TTS, Underdog Woof non-commercial terms, Cartesia terms of service).
Available Tools
4 toolslist_providersA
List configured TTS providers and whether each is currently healthy.
Inputs: no named parameters. Returns: result
list_voicesA
List voices for one provider, or all configured providers when omitted.
Inputs: provider. Returns: result
provider_statusB
Health-check one provider, or all configured providers when omitted.
Inputs: provider. Returns: result
synthesizeA
Synthesize speech to a WAV file and return its absolute path plus metadata.
Args: text: Spoken line to generate. provider: piper | pocket | woof | cartesia (default from env / first healthy local). voice: Provider-specific voice id or name (Pocket also accepts an audio prompt URL). filename_hint: Optional short label included in the output filename.
Inputs: text (required), voice, provider, filename_hint. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
list_providers and provider_status overlap substantially since list_providers already reports health, making the dedicated health-check largely redundant and easy to misselect. list_voices and synthesize are clearly distinct, so the overlap is confined to two tools.
Three tools use verb_noun (list_providers, list_voices) or bare verb (synthesize), while provider_status uses a noun_noun form, breaking the pattern. Mixed conventions but still readable.
Four tools is on the lean side but appropriate for a focused TTS server: provider discovery, health, voices, and synthesis. The only inefficiency is the split between list_providers and provider_status, which could be consolidated.
The core TTS lifecycle (discover providers, list voices, synthesize to WAV) is well covered. Minor gaps exist around listing/managing generated audio files or configuring providers, but agents can work around these.
Maintenance
Related MCP Connectors
Synthesize short texts into WAV audio using offline formant voices in English, German and Spanish
AI Voice Production Agent: picks from 30+ TTS models, fixes pronunciation, validates every line.
Cartesia voice AI: text-to-speech, speech-to-text, voice cloning, and voice management.
Transcribe, subtitle, dub and lip-sync media; create speech, voices, images and thumbnails.
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceEnables text-to-speech generation, voice cloning, dialogue creation, and other TTS operations through natural language in MCP-compatible AI assistants.20 npmMIT- FlicenseNot gradedqualityBmaintenanceEnables AI agents to generate narration in a single fixed, pre-approved voice, returning audio with per-line timing, hashes, and automatic quality checks on content, speaker identity, and pace, all locally and reproducibly.-
- AlicenseNot gradedqualityBmaintenanceEnables coding agents to generate local GPU-accelerated narration audio from text, with tools for speech generation, job continuation, and model or voice queries.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to manage voices and generate speech, multi-character dubbing, and batch audio through a local TTS service, including health checks and job polling.Apache 2.0