BreezeBlue releases Breeze-TTS-2, a 3B English and Chinese TTS, non-commercial
Breeze-TTS-2 is a roughly 3B bilingual TTS with cloning, voice design and streaming; weights under a non-commercial licence.
The AI that actually shipped
Breeze-TTS-2 is a roughly 3B bilingual TTS with cloning, voice design and streaming; weights under a non-commercial licence.
Qwen3.8-27B is a dense 27B model with a vision encoder, 262,144-token native context and switchable thinking, under Apache 2.0.
MagpieTTS Multilingual 357M v2607 covers 12 languages with five preset voices; voice cloning was removed. NVIDIA Open Model License.
Kimi K3 is a 2.8T mixture-of-experts model with 104B active parameters and 1M-token context, under the Kimi K3 License.
Higgs TTS 3 is a roughly 4B voice-cloning TTS with inline control tags and 100+ languages; research and non-commercial licence.
Step 3.7 Flash is a 198B sparse MoE vision-language model with about 11B active parameters and 256k context, under Apache 2.0.
Supertonic 3 is a roughly 99M ONNX TTS for local and browser use across 31 languages; OpenRAIL-M model, MIT sample code.
Granite 4.1 8B is a long-context instruct model with better tool calling and instruction following, under Apache 2.0.
VoxCPM2 is a 2B tokenizer-free TTS covering 30 languages, with voice design, cloning and 48 kHz output, under Apache 2.0.
Mistral Medium 3.5 is a dense 128B instruct, reasoning and coding model with 256k context. The licence excludes large-revenue companies.