Gradium TTS lands on Baseten with 50ms TTFA for full voice agent pipelines
mattturck · x · 2026-10-14
- Gradium's text-to-speech model is now in the Baseten Model Library, letting existing Baseten users deploy it in one click.
- Ultra-low latency: 50ms time-to-first-audio (sub-100ms TTFA), enabling full voice agent pipelines with any transcription model and LLM on Baseten.
- Self-hosted deployments use the same streaming WebSocket protocol as the hosted API (requires Gradium SDK ≥0.6.1); custom voices and pronunciation dictionaries are hosted-API only.
Related event: Gradium TTS Lands on Baseten with 50ms Latency(2 posts)→
More from Infra
- Sniffed the network traffic of Ollama and LM Studio: chats stay local, apps don't — TheOyinbooke · 2026-10-14
- First real-world look at Google's Ironwood TPU rack at Google Cloud event — firstadopter · 2026-10-14
- Samsung shows off HBM5 samples and Custom HBM with xPU stacked design — firstadopter · 2026-10-14
- AWS launches Lambda Web Functions with up to 128 concurrent requests per environment — tlakomy · 2026-10-14
- Bosch and Rittal show massive manifolds for MW liquid cooling and 800VDC — BenBajarin · 2026-10-14
- OCP Global Summit sponsor wall shows Nvidia, AMD, Google Cloud, Meta and hundreds more — firstadopter · 2026-10-14