MCP For Claude Marketplace
Cartesia (Voice AI)

Cartesia (Voice AI) MCP Connector for Claude

A+

Generate lifelike AI voices, clone speech, and transcribe audio with Cartesia's state-of-the-art Sonic models directly from your AI agent.

20 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect Cartesia to your AI agent to unlock high-performance voice synthesis and speech recognition. Cartesia's Sonic models provide industry-leading latency and quality for real-time applications.

What you can do

  • Text-to-Speech (TTS) — Generate high-fidelity audio bytes or stream via SSE using models like Sonic 3.5 and Sonic 3.
  • Speech-to-Text (STT) — Transcribe audio files into text using the Ink Whisper model with multi-language support.
  • Voice Cloning — Create custom voice models from as little as 5 seconds of audio input.
  • Voice Management — List, retrieve, and update voices, or use the Voice Changer to transform existing audio.
  • Pronunciation Control — Manage custom pronunciation dictionaries for specialized terminology or accents.
  • Agent Orchestration — List and manage AI agents and monitor call logs and usage credits.

How it works

  1. Subscribe to this server
  2. Enter your Cartesia API Key
  3. Start generating audio or transcribing speech from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Developers — integrate real-time voice synthesis into applications without managing complex infrastructure.
  • Content Creators — automate voiceovers and audio localization using high-quality cloned voices.
  • Product Teams — build conversational AI agents that sound human and respond with sub-second latency.
text-to-speechspeech-to-textvoice-synthesislow-latencyai-voiceaudio-streaming

20 tools expose this connector's capabilities to your AI agent.

delete_pronunciation_dict

Provide the dictionary ID to confirm deletion. Delete a pronunciation dictionary

generate_access_token

Generate a short-lived access token for client-side requests

get_agent

Supply the agent ID to query the data. Get details for a specific voice agent

get_usage_credits

Get credit usage statistics

infill_bytes

Provide the audio clips, text, and voice ID. Generate audio to smoothly connect two existing segments

list_agent_calls

Provide the agent ID to filter results. List calls and transcripts for a specific agent

list_voices

List available voices

list_agents

List all voice agents

list_pronunciation_dicts

List pronunciation dictionaries

tts_sse

Generate text-to-speech via Server-Sent Events

update_pronunciation_dict

Supply the dictionary ID and the new name. Update a pronunciation dictionary

stt_batch

Transcribe audio file to text (Batch STT)

tts_bytes

Generate text-to-speech audio bytes

clone_voice

Clone a voice from a 5s audio clip

create_pronunciation_dict

Specify both the name and the language code. Create a new pronunciation dictionary

delete_voice

Use the voice ID to confirm deletion. Delete a voice

get_voice

Provide the voice ID to query the data. Get details for a specific voice

localize_voice

Supply the original voice ID and target language. Adapt a voice to a new language/dialect

update_voice

Supply the voice ID and the fields to update. Update voice metadata

voice_changer_bytes

Provide the audio clip and target voice ID. Change voice of an audio clip while preserving intonation

See how to talk to your AI agent using Cartesia (Voice AI).

List all available voices in my Cartesia account.

I've retrieved the list of voices. You have access to several models, including 'Baritone' (ID: 79a045e3...), 'British Lady' (ID: 123x-456y...), and your custom cloned voices. Which one would you like to use?

Generate a WAV audio file saying 'Welcome to the future of AI' using voice ID 79a045e3-a621-4923-b05c-8029db0dffca.

Generating audio... I've synthesized the text using the Sonic-3.5 model. The WAV file is ready for download.

Check my current usage credits on Cartesia.

You currently have 45,200 credits remaining in your account. Your last billing cycle refreshed on the 1st of the month.

Yes. Using the `tts_bytes` tool, you can specify the `output_format_container` as 'mp3', 'wav', or 'raw', and configure the sample rate and encoding to match your needs.

Related Connectors

iFLYTEK Open Platform / 讯飞开放平台

iFLYTEK Open Platform / 讯飞开放平台 MCP

8 tools Official

China's leading voice and NLP platform — convert speech to text, synthesize voice, and analyze text via AI.

A+ View details →
Maestra

Maestra MCP

8 tools Official

Automate transcription, translation, and AI voiceovers via the Maestra.ai REST API.

A+ View details →
Spiritme

Spiritme MCP

12 tools Official

Create AI-generated videos with digital human presenters that deliver personalized messages in multiple languages naturally.

A+ View details →
Rev.ai

Rev.ai MCP

19 tools Official

High-accuracy speech-to-text and transcription — submit media files, generate AI summaries, and create captions directly from your AI agent.

A+ View details →