transformers serve adds OpenAI-compatible /v1/audio/speech, debuts Gradium's 40M on-device TTS
yb2698 · x · 2026-10-21
Hugging Face's transformers serve now exposes an OpenAI-compatible /v1/audio/speech endpoint, launched with Gradium's brand-new on-device TTS model Phonon — tiny, fast and multilingual at the 40M scale. Run it with transformers serve gradium/phonon-40m-en, making local speech synthesis trivially accessible via the OpenAI-style API.
More from Infra
- Liquid AI Launches RIPL: Ultra-Low-Latency Inference Engine With Sub-50ms End-to-End Responses — JosephJacks_ · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Jensen Huang lays out NVIDIA's full Vera Rubin agentic system: NVL72, MGX, CMX and RTX — rohanpaul_ai · 2026-10-23
- ONNX to Transformers.js: running models directly in your browser — JosephJacks_ · 2026-10-23
- MiniMax M3.1 Flash free for 3 days on 0G, with 1M context and 512K output — MiniMax_AI · 2026-10-23
- "We bet on Cloudflare and it paid off": R2 and D1 at billion scale — dinasaur_404 · 2026-10-23