# Tagged multilingual-tts

> Announcements and real-world deployments of AI, checked against their sources and scored: open-weights releases, decision models in the wild, and what is actually in use.

- [Fish Audio releases Drama 3, a 35B mixture-of-experts TTS for multi-character scenes](https://shipped.anth.us/open-weights/fish-audio-drama-3/index.md): Drama 3 is a 35B MoE speech model (3B active) with up to 16 speaker tags and voice cloning; research licence. (2026-10-01)
- [NVIDIA releases MagpieTTS Multilingual 357M v2607, 12 languages with preset voices](https://shipped.anth.us/open-weights/nvidia-magpie-tts-multilingual-357m/index.md): MagpieTTS Multilingual 357M v2607 covers 12 languages with five preset voices; voice cloning was removed. NVIDIA Open Model License. (2026-07-21)
- [Boson AI releases Higgs TTS 3, a 4B zero-shot voice cloning model for 100+ languages](https://shipped.anth.us/open-weights/boson-ai-higgs-tts-3/index.md): Higgs TTS 3 is a roughly 4B voice-cloning TTS with inline control tags and 100+ languages; research and non-commercial licence. (2026-06-04)
- [Supertone releases Supertonic 3, a 99M on-device TTS in 31 languages](https://shipped.anth.us/open-weights/supertone-supertonic-3/index.md): Supertonic 3 is a roughly 99M ONNX TTS for local and browser use across 31 languages; OpenRAIL-M model, MIT sample code. (2026-05-06)
- [OpenBMB releases VoxCPM2, a 2B Apache 2.0 TTS with voice design and 48 kHz output](https://shipped.anth.us/open-weights/openbmb-voxcpm2/index.md): VoxCPM2 is a 2B tokenizer-free TTS covering 30 languages, with voice design, cloning and 48 kHz output, under Apache 2.0. (2026-04-03)
- [k2-fsa releases OmniVoice, a 0.6B zero-shot TTS covering 600+ languages](https://shipped.anth.us/open-weights/k2-fsa-omnivoice/index.md): OmniVoice is a 0.6B voice-cloning and voice-design TTS tagged for 646 languages; code Apache 2.0, weights CC-BY-NC. (2026-03-30)
- [Mistral releases Voxtral TTS, a 4B open-weights speech model, non-commercial](https://shipped.anth.us/open-weights/mistral-voxtral-tts/index.md): Voxtral 4B TTS covers nine languages with 20 preset voices and streaming; weights are CC BY-NC 4.0. (2026-03-26)
- [Fish Audio releases S2 Pro, a 5B TTS model for 80+ languages, research licence](https://shipped.anth.us/open-weights/fish-audio-s2-pro/index.md): S2 Pro is a dual-autoregressive TTS model with inline emotion tags; weights are free for research, commercial use needs a licence. (2026-03-09)
- [OpenMOSS Team releases MOSS-TTS, an 8B Apache 2.0 voice cloning and long-form TTS](https://shipped.anth.us/open-weights/openmoss-moss-tts/index.md): MOSS-TTS is an 8B (and 1.7B) open TTS family with cloning, up to an hour of long-form audio and duration control. (2026-02-06)
- [Qwen releases Qwen3-TTS, Apache 2.0 voice cloning in 10 languages](https://shipped.anth.us/open-weights/alibaba-qwen3-tts/index.md): 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. (2026-01-22)

Page 1 of 2 · [next](https://shipped.anth.us/tags/multilingual-tts/page/2/index.md)