three.ws Audio
Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D…
- Pricing
- Open source
- Runs
- Locally
- Version
- 0.1.3
- Listing updated
- 5 days ago
About three.ws Audio
three.ws Audio is an open-source MCP server for design and media. It runs locally on your machine and is started by your AI client.
Text-to-speech, speech-to-text, audio-to-face lipsync, and motion-capture clips for 3D agents.
Install
Run in a terminal
claude mcp add audio-mcp --env THREE_WS_API_KEY='<THREE_WS_API_KEY>' -- npx -y @three-ws/audio-mcpAdd to claude_desktop_config.json
{
"mcpServers": {
"audio-mcp": {
"command": "npx",
"args": [
"-y",
"@three-ws/audio-mcp"
],
"env": {
"THREE_WS_API_KEY": "<THREE_WS_API_KEY>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"audio-mcp": {
"command": "npx",
"args": [
"-y",
"@three-ws/audio-mcp"
],
"env": {
"THREE_WS_API_KEY": "<THREE_WS_API_KEY>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"audio-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@three-ws/audio-mcp"
],
"env": {
"THREE_WS_API_KEY": "<THREE_WS_API_KEY>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"audio-mcp": {
"command": "npx",
"args": [
"-y",
"@three-ws/audio-mcp"
],
"env": {
"THREE_WS_API_KEY": "<THREE_WS_API_KEY>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"audio-mcp": {
"command": "npx",
"args": [
"-y",
"@three-ws/audio-mcp"
],
"env": {
"THREE_WS_API_KEY": "<THREE_WS_API_KEY>"
}
}
}
}Configuration
THREE_WS_BASEBase URL of the three.ws API that serves the audio/animation endpoints. Override only when self-hosting or targeting a preview deployment.THREE_WS_API_KEYOptional three.ws API key (bearer token). Raises the metered TTS/ASR/Audio2Face rate limits and unlocks your own private/unlisted motion-capture clips. Leave unset to use the public surface anonymously.THREE_WS_TIMEOUT_MSPer-request timeout in milliseconds for the live audio/animation calls (synthesis and recognition are real upstream model calls).
Pricing
Open source
Prices change. Check three.ws before you buy.
three.ws Audio FAQ
Is three.ws Audio free?
Yes. three.ws Audio is open source, so you can use and self-host it for free.
How do I add three.ws Audio to Claude Code?
Run this command in your terminal: claude mcp add audio-mcp --env THREE_WS_API_KEY='<THREE_WS_API_KEY>' -- npx -y @three-ws/audio-mcp
What are the best alternatives to three.ws Audio?
The closest alternatives to three.ws Audio are HyperFrames by HeyGen, ffmpeg-skill, AvatarSay — Fictional Character & Talking Video MCP, ChartAnt and VfxSmith.
Alternatives to three.ws Audio

HyperFrames by HeyGen
MCP serverHosted MCP connector for creating and rendering videos from HTML through AI chat
- Remote
- Freemium
- 85.3K GitHub stars
- Design and media

ffmpeg-skill
MCP serverLocal FFmpeg video and audio editing tools for coding agents over MCP
Runs locally- Open source
- 6.9K GitHub stars
- Design and media

Generate fictional character portraits and lip-synced talking videos from text over MCP
- 10 tools
- Remote
- Freemium
- Design and media

ChartAnt
MCP serverRemote MCP server returning charts, maps and dashboards as hosted PNG links
- 51 tools
- Remote
- Freemium
- Design and media

VfxSmith
MCP serverSearch, generate, refine and export pixel art game effects from Claude Code or Codex
Not checked yet- Remote
- Freemium
- Design and media

CalderFlow
MCP serverTurn notes or specs into editable flowcharts, timelines and funnels from an AI assistant
- 10 tools
- Remote
- Free
- Design and media