In the news
Gradium TTS on LiveKit Inference
Gradium · Published · 3 min read
In 30 seconds
- What happened
- Gradium Text-to-Speech is now available on LiveKit Inference, free through October 9, with voice cloning and sub-250ms latency.
- Why it matters
- Matters for engineers building voice agents on LiveKit who need low-latency conversational speech synthesis without managing separate vendor accounts.
- Watch out
- Free tier ends October 9. Requires LiveKit Agents framework. Text normalization is built-in but pronunciation robustness depends on specific use cases.
- inference
The patterns behind this
Each one covers how the technique works, when it earns its cost, and where it breaks.
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.