Cartesia
Ultra-low-latency voice AI platform built on state-space models for real-time speech synthesis and interactive voice agents.
Speech synthesis, voice cloning, transcription and meeting notes.
Ultra-low-latency voice AI platform built on state-space models for real-time speech synthesis and interactive voice agents.
Enterprise voice AI API platform delivering streaming speech-to-text, diarization, timestamps, text-to-speech, and voice agents.
Multilingual AI voice synthesis, voice cloning, dubbing, and conversational voice agent platform with low-latency streaming APIs.
Open-source-backed multilingual text-to-speech and zero-shot voice cloning platform strong in Chinese, English, and Japanese.
Lightweight open-weight Apache-2.0 text-to-speech model designed for fast, natural local speech generation on modest hardware.
AI music and vocal creation studio turning lyrics, styles, and audio prompts into complete full-length songs with vocals.
Generative music studio focused on studio-grade vocal clarity, section-by-section arrangement, inpainting, and stem workflows.