AI · GitHub repo
cartesia-python
Official Python library for Cartesia's real-time text-to-speech API
cartesia-python is the official client library for interacting with Cartesia's Sonic text-to-speech models in Python. It supports synchronous and asynchronous HTTP requests alongside WebSocket streaming for low-latency audio generation. It is designed for developers building voice agents and real-time speech applications.
What it's for
- Stream real-time text-to-speech audio from LLM output over WebSockets
- Generate WAV or PCM voice audio files from text transcripts
- Integrate voice cloning and custom voice playback into Python applications
- Manage and paginate through Cartesia voice datasets and profiles
Features
- Synchronous and asynchronous clients powered by httpx and optional aiohttp backend
- Full WebSocket streaming support for low-latency chunked audio generation
- Pydantic response models and TypedDict request parameters for editor autocomplete
- Built-in automatic pagination for voice and dataset listing
- Automatic retries with exponential backoff for rate limits and connection errors
- Granular audio formatting controls including container, encoding, and sample rate
Pricing
Paid. Open-source SDK, requires a paid Cartesia API key
Details
- Type
- GitHub repo
- Category
- AI
- Topic
- Text to Speech
- Open source
- Yes
- Platforms
- Code library, API
- For
- Python developers building voice agents, audio tools, and AI assistants
- Alternative to
- elevenlabs, deepgram, openai
- Tags
- tts, text to speech, voice, audio, cartesia, python sdk, websockets
Why it was saved
- @svpino: For integrating voice cloning / voice agents into products in Python.
Compare
Related
AI voice generator, voice cloning, and conversational agent platform
Ultra-low-latency streaming text-to-speech and instant voice cloning model.
Open-source 1.6B text-to-speech model generating multi-speaker dialogue in one pass.
Fast, low-cost text-to-speech API and studio for creators and developers
Converts spoken thoughts into structured, polished writing in customizable styles.
Open-source zero-shot text-to-speech and voice cloning model
Updated