Gradium TTS is now available on LiveKit Inference, free until Oct. 9. Gradium TTS is designed for conversational use cases, with voice cloning, low latency (below 250ms TTFA), and robust pronunciation on difficult cases. Select @GradiumAI as your TTS provider in LiveKit Inference, no additional account or API key required:

Audio8 TTS Preview 0.1B — now on Hugging Face as ONNX INT8 ~100M params · 11 languages · zero-shot voice cloning Runs on CPU only (~0.4 GB RAM) — no PyTorch, no CUDA 44.1 kHz · OpenAI-compatible API · Apache 2.0 Try it 👇 #TTS# #VoiceCloning# #ONNX# #OpenSource#

Modern TTS models can sound great — and still fail badly on pacing, pauses, and prosody. We adapted DPO + GRPO to flow-matching models to tackle the tail end of TTS behavior:

Grok TTS just took the top spot on The Humanness Index It scored 94 for humanness....just six points below the human baseline of 100 and achieved the highest model rating Even the cost difference is insane: • Grok TTS: $15 • Eleven v3: $100 Grok delivers the higher human-likeness score while costing nearly 7× less than the next model It is also faster, with 460 ms latency compared with 758 ms for Eleven v3 Grok TTS is delivering top-tier voice quality without the premium price

this TTS model generates speech 167x faster than you can hear it. Supertonic is an on-device TTS engine that runs via ONNX for cross-platform inference. - no GPU - 31 languages - captures every emotion - beats ElevenLabs on speed - runs even on a Raspberry Pi 100% open-source.

Gemini 3.8 TTS is live on AI Gateway. 100+ languages. Try both models: • 𝚐𝚘𝚘𝚐𝚕𝚎/𝚐𝚎𝚖𝚒𝚗𝚒-𝟹.𝟾-𝚏𝚕𝚊𝚜𝚑-𝚕𝚒𝚝𝚎-𝚝𝚝𝚜 • 𝚐𝚘𝚘𝚐𝚕𝚎/𝚐𝚎𝚖𝚒𝚗𝚒-𝟹.𝟾-𝚏𝚕𝚊𝚜𝚑-𝚝𝚝𝚜

Gemini 3.8 Flash TTS and Flash-Lite TTS from Google (@Google) are now available on Merge Gateway. They take the top two spots on Hume AI's Overall Quality Index, and Flash TTS leads the Voice Design Benchmark at 71.4.

BREAKING: Freya TTS Adam v1 by @FreyaVoice takes the #1# spot on AudioRealismBench with an Elo of 1418. The model ranks ahead of Bland Speech v3 by @usebland and Kalpa TTS Beta v0.1 by @KalpaLabsAI. AudioRealismBench measures how human-like speech sounds through blind comparisons by vetted native speakers across phone agents, conversational assistants, and spoken explainers. Congratulations to @TungaBayrak and the entire @FreyaVoice team. We’re excited to see what comes next!