Gradium TTS beta model is out now to define what fast means.
This is a AI post classified by Jev as Voice AI (a launch), kept by the AI Radar because it carries real work, not commentary.
Gradium TTS beta model is out now to define what fast means. Less than 50ms TTFA, same quality. Most models are >100ms TTFA. Try it now: https://studio.gradium.ai/?model_name=gradium-tts-beta
Posted by Gradium (4.4k followers) 2 h ago · 36 likes · 1.6k views · view the original post on X. Kept by the AI Radar as Voice AI. Tools mentioned: studio.gradium.ai.
More AI work like this
- This is mindblowing. Your Tesla can now manage your inbox, calendar, and tasks while you… — @VaibhavSisinty
- Use Opus 5.5 on MEDIUM! — @AdamHoltererer
- New model: gemini-3.8-flash-tts — @aitrackerbot
- New model: gemini-3.8-flash-lite-tts — @aitrackerbot
- Jev + on-device models = results in seconds with no LLM in the loop. — @desertantlabs
- We’re releasing Scribe v2 Medical, our speech-to-text model fine-tuned for clinical audio. — @ElevenLabs
- 🎙️ Real-time interpretation, powered locally by VoxCPM2. — @OpenBMB
- If your voice interaction is failing, you should be able to know why. — @ai_coustics
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 42.6k posts from 5k X accounts over the last 14 days, 1.8k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 18:12 UTC. Full method.