
Cartesia
Cartesia voice AI: text-to-speech, speech-to-text, voice cloning, and voice management.
- GitHub stars
- 18
- tools
- 20
- auth
- Secret needed
- transport
- STDIO, HTTP
- env vars
- 3
- last updated
- Nov 18, 2026
Tools
20 toolsPublic tool metadata for what this MCP can expose to an agent.
text_to_speechConvert text to audio; optional output_path (local server), speed, volume, emotion, and pronunciation dict. Default save=true returns file_id and a 24h download_url.
Convert text to audio; optional output_path (local server), speed, volume, emotion, and pronunciation dict. Default save=true returns file_id and a 24h download_url.
No parameter schema in public metadata yet.
speech_to_textTranscribe audio from file_id or a server file_path (mode=batch default, or mode=stream)
Transcribe audio from file_id or a server file_path (mode=batch default, or mode=stream)
No parameter schema in public metadata yet.
list_voicesList available voices (filter by language, search, gender, etc.)
List available voices (filter by language, search, gender, etc.)
No parameter schema in public metadata yet.
get_voiceFetch metadata for a voice by ID
Fetch metadata for a voice by ID
No parameter schema in public metadata yet.
clone_voiceClone a voice from file_id or a server file_path
Clone a voice from file_id or a server file_path
No parameter schema in public metadata yet.
update_voiceUpdate a cloned voice's name or description
Update a cloned voice's name or description
No parameter schema in public metadata yet.
delete_voiceDelete a cloned voice
Delete a cloned voice
No parameter schema in public metadata yet.
localize_voiceAdapt a voice to another language or dialect
Adapt a voice to another language or dialect
No parameter schema in public metadata yet.
list_accentsList catalog accent IDs and metadata (british, standard-japanese, …)
List catalog accent IDs and metadata (british, standard-japanese, …)
No parameter schema in public metadata yet.
list_modelsList callable Sonic (TTS) and Ink (STT) model ids (capability=tts|stt)
List callable Sonic (TTS) and Ink (STT) model ids (capability=tts|stt)
No parameter schema in public metadata yet.
list_agent_modelsList Managed Agents LLM ids from GET /v1/agents/models (full catalog)
List Managed Agents LLM ids from GET /v1/agents/models (full catalog)
No parameter schema in public metadata yet.
add_voice_accentsAdd catalog accents to an instant voice clone (british, parisian, …)
Add catalog accents to an instant voice clone (british, parisian, …)
No parameter schema in public metadata yet.
delete_voice_accentRemove a catalog accent from an instant voice clone
Remove a catalog accent from an instant voice clone
No parameter schema in public metadata yet.
list_pronunciation_dictsList pronunciation dictionaries
List pronunciation dictionaries
No parameter schema in public metadata yet.
create_pronunciation_dictCreate a pronunciation dictionary
Create a pronunciation dictionary
No parameter schema in public metadata yet.
get_pronunciation_dictGet a pronunciation dictionary by ID
Get a pronunciation dictionary by ID
No parameter schema in public metadata yet.
update_pronunciation_dictUpdate a pronunciation dictionary
Update a pronunciation dictionary
No parameter schema in public metadata yet.
delete_pronunciation_dictDelete a pronunciation dictionary
Delete a pronunciation dictionary
No parameter schema in public metadata yet.
download_fileFetch a cloud file by ID (download_url + local copy)
Fetch a cloud file by ID (download_url + local copy)
No parameter schema in public metadata yet.
get_credit_usageCredit usage over time (CARTESIA_ADMIN_API_KEY)
Credit usage over time (CARTESIA_ADMIN_API_KEY)
No parameter schema in public metadata yet.
Sponsors
Configuration
CARTESIA_API_KEY*secretCartesia API key from https://play.cartesia.ai/keys
CARTESIA_ADMIN_API_KEYsecretOptional admin API key for credit usage tools
OUTPUT_DIRECTORYDirectory where generated and downloaded audio files are written
Readme
Cartesia MCP Server
The Cartesia MCP server exposes Cartesia APIs over the Model Context Protocol (MCP) so clients such as Cursor, Claude Desktop, and OpenAI Agents can list voices, run TTS and STT, manage pronunciation dictionaries, clone voices, and more—without one-off scripts.
Documentation: Cartesia docs — MCP
Setup
Hosted (recommended) — connect to https://mcp.cartesia.ai/mcp and sign in when prompted. A Cartesia MCP API key is created for your organization if one does not exist yet. You can also connect from API Keys in the Playground.
Cursor — Install Cartesia MCP, then sign in to the Playground when your browser opens.
Claude Code:
Details
- Repository
- github.com/cartesia-ai/cartesia-mcp
- Website
- docs.cartesia.ai/tools/ai/mcp
- Category
- Media & Entertainment
- Package
cartesia-mcp- Transport
- STDIO, HTTP
- Auth
- Required
- Registry
- MCP registry, active