k2-fsa releases OmniVoice, a 0.6B zero-shot TTS covering 600+ languages
OmniVoice is a 0.6B voice-cloning and voice-design TTS tagged for 646 languages; code Apache 2.0, weights CC-BY-NC.
Open weights
Mistral releases Voxtral TTS, a 4B open-weights speech model, non-commercial
Voxtral 4B TTS covers nine languages with 20 preset voices and streaming; weights are CC BY-NC 4.0.
Google DeepMind releases Gemma 4, with a 31B dense model under Apache 2.0
Gemma 4 comes in five sizes from E2B to 31B, with multimodal input, 256K context on the larger models and an Apache 2.0 licence.
Fish Audio releases S2 Pro, a 5B TTS model for 80+ languages, research licence
S2 Pro is a dual-autoregressive TTS model with inline emotion tags; weights are free for research, commercial use needs a licence.
NineNineSix releases KaniTTS2-en, a 400M English TTS with voice cloning
KaniTTS2-en is a 400M English TTS on LFM2 350M with cloning via a speaker embedder, about 3 GB VRAM; LFM 1.0 licence.
OpenMOSS Team releases MOSS-TTS, an 8B Apache 2.0 voice cloning and long-form TTS
MOSS-TTS is an 8B (and 1.7B) open TTS family with cloning, up to an hour of long-form audio and duration control.
Qwen releases Qwen3-TTS, Apache 2.0 voice cloning in 10 languages
Qwen3-TTS is a family of open TTS models, 0.6B and 1.7B, with 3-second voice cloning, voice design and streaming, under Apache 2.0.
Hume AI releases TADA-1B, an English TTS that aligns one speech vector per text token
TADA-1B is Hume AI's open English TTS built on Llama 3.2 1B, with 1:1 text-to-speech alignment; Llama 3.2 licence.
Soprano-80M: an 80M Apache 2.0 TTS that claims 2000x real time on GPU
Soprano-80M is a tiny English-only TTS with under 15 ms streaming latency on GPU, no cloning, Apache 2.0; superseded by Soprano 1.1.
FunAudioLLM releases Fun-CosyVoice3-0.5B-2512, an Apache 2.0 voice cloning TTS
Fun-CosyVoice3 is a 0.5B zero-shot cloning TTS for nine languages and 18+ Chinese dialects, with latency down to 150 ms.