Chatterbox
MIT · Open source
MIT-licensed TTS from Resemble AI. Chatterbox Multilingual V3 is a 500M model for 23 or more languages with zero-shot cloning.
Voice models
Open text-to-speech and voice-clone models people wire into agents.
Voice models synthesize speech. They show up in agent stacks as the voice of a realtime assistant. Pages here stick to license, size, and language claims printed on the model card or repository.
Launches
Newest firstNo launches in this category yet.
Tools in this category
Kokoro
Apache-2.0 · Open source
Apache-2.0 TTS model with 82 million parameters. Version 1.0, published January 27, 2025, lists 8 languages and 54 voices.
MOSS-TTS
Apache-2.0 · Open source
Apache-2.0 speech family from OpenMOSS. MOSS-TTS-v1.5 supports 31 languages, with separate models for realtime streaming and voice design.
Qwen3-TTS
Apache-2.0 · Open source
Apache-2.0 speech models from the Qwen team, 0.6B and 1.7B, with voice clone, voice design, and 10 languages.
VoxCPM
Apache-2.0 · Open source
Apache-2.0 tokenizer-free TTS from OpenBMB. VoxCPM2 is a 2B model with 30 languages, voice design, cloning, and 48 kHz output.