Price
Free $0/month · Paid from $5/month
AI / Voice Cloning & Voice Conversion / Cartesia
Cartesia Sonic
Real-time AI text-to-speech model for natural, low-latency voice generation and voice cloning.
TTSVoice CloningReal-time AudioMultilingual SpeechVoice Agents
Specialization
TTS · Voice Cloning · Real-time Audio · Multilingual Speech · Voice Agents
Quality
Natural, expressive speech optimized for real-time conversations.
Features
Voice Cloning · API · Streaming · Multilingual · Voice Library
About Cartesia Sonic
Cartesia Sonic is a real-time text-to-speech model designed for natural conversational speech, voice agents, multilingual generation and low-latency streaming. The current Sonic 3.6 generation supports native speech in 44 languages and custom voice cloning.
Specifications
Capabilities
6 specifications +
| Text-to-Speech | Yes |
| Voice cloning | Instant and Professional |
| Supported languages | 44 languages |
| Real-time audio | Yes |
| Emotion control | Emotion and expressive controls |
| Voice library | Available |
Developer
3 specifications +
| API access | Yes |
| SDK availability | SDKs available |
| Commercial Use | Included on paid plans |
Languages & Voices
1 specifications +
| Voice Library | Available |
Commercial & Business
1 specifications +
| Commercial Use | Included on paid plans |
