mcp.film / Voice & Dialogue / Cartesia MCP
Cartesia MCP
Official Cartesia (Sonic) server: low-latency TTS, voice cloning, infill, localization.
What it does
Cartesia's official MCP server exposes its Sonic voice stack: TTS, speech-to-text, voice cloning, voice changing, and notably audio infill (generate speech between two existing clips) and voice localization into other languages. Strong for ADR-style dialogue patching and localizing a character's voice across language versions.
Connect
claude mcp add cartesia -e CARTESIA_API_KEY=YOUR_KEY -- uvx cartesia-mcp
{
"mcpServers": {
"cartesia": {
"command": "uvx",
"args": [
"cartesia-mcp"
],
"env": {
"CARTESIA_API_KEY": "YOUR_KEY_HERE"
}
}
}
}
{
"mcpServers": {
"cartesia": {
"command": "uvx",
"args": [
"cartesia-mcp"
],
"env": {
"CARTESIA_API_KEY": "YOUR_KEY_HERE"
}
}
}
}
CARTESIA_API_KEY — https://play.cartesia.ai/keys
Tools you'll see
text_to_speechspeech_to_textlist_voicesclone_voicevoice_changelocalize_voiceinfillget_credit_usageField notes
Officially supported, on PyPI as cartesia-mcp; ~16 tools. Optional CARTESIA_ADMIN_API_KEY enables account-management tools; OUTPUT_DIRECTORY controls where audio is saved.
Pairs well with
MartiniMartini
Official
The film set for AI videos — direct entire productions from your agent.
Airtable MCP ServerAirtable
Official
Official hosted Airtable MCP: query, create, and update production-tracking bases.
AudioGen MCPpeerjakobsen
Free, local sound-effect generation with Meta's AudioGen — no API key needed.