29 speech-to-speech model launches in one year — when does s2s overtake cascades?
rdesh26 · x · 2026-11-05
yizbebuilding compiled every model launched in the past year (Nov 2025–Oct 2026) marketed as speech-to-speech, full-duplex, or both — 29 verified launches in total, charted on a timeline. The list spans OpenAI GPT-Realtime models, xAI Grok Voice 1.0–3.0, Google Gemini Live variants, Amazon Nova Sonic series, ByteDance Seedduplex/SeedRealtime, Alibaba Qwen-Audio line, NVIDIA PersonaPlex/NemoTron, KRAFTON SpeechChat-9B, and Thinking Machines TML-1. The author asks: when will s2s models overtake cascade pipelines in production?
More from Multimodal
- One prompt builds an interactive 3D alpine valley with Tencent Hunyuan Hy4 — no models, no textures, all code — Aiden_Tech_Ai · 2026-11-05
- A total beginner made an ad in under 10 minutes by pasting one link into Claude — PrajwalTomar_ · 2026-11-05
- 10 open-source GitHub repos for voice AI: cloning, TTS, and phone-call agents — victor_explore · 2026-11-05
- Generative world demo shows riverside scene with motorbike, bow and fishing rod — wavefnx · 2026-11-05
- Blender 5.3 to support Gaussian Splatting natively; SuperSplat extension eases imports — willeastcott · 2026-11-05
- SenseTime open-sources SenseNova 6.8 Code2Video, a code-first editable video generation model — s_mohinii · 2026-11-05