# Tagged low-latency

> 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.

- [Soprano-80M: an 80M Apache 2.0 TTS that claims 2000x real time on GPU](https://shipped.anth.us/open-weights/ekwek-soprano-80m/index.md): Soprano-80M is a tiny English-only TTS with under 15 ms streaming latency on GPU, no cloning, Apache 2.0; superseded by Soprano 1.1. (2025-12-22)
- [Microsoft releases VibeVoice-Realtime-0.5B, a streaming TTS model under MIT](https://shipped.anth.us/open-weights/microsoft-vibevoice-realtime-0-5b/index.md): A single-speaker streaming TTS model that starts speaking in about 300 ms; MIT licensed, but the card says research use only. (2025-12-04)
- [Resemble AI releases Chatterbox-Turbo, a 350M MIT TTS built for voice agents](https://shipped.anth.us/open-weights/resemble-ai-chatterbox-turbo/index.md): Chatterbox-Turbo is a 350M English TTS with paralinguistic tags, one-step decoding and voice cloning; MIT licensed and watermarked. (2025-12-02)