Topic
All blog posts, tools, and guides about Voice AI from Developers Digest.
6 resources - 6 posts

The Gemini API shuts down two Live API preview models and three TTS preview models on November 17, 2026. Replacement ids, what changes in the session config and TTS request, prices before and after, and the code change.

GPT-Live can now call the Decisions API itself, mid-sentence. How native delegation and transcript triggers work, the session config, and the events to handle.

OpenAI prompt-to-voice turns a text description into a saved GPT-Live voice. Creating it is free, the limit is 100 per org, and it only works in GPT-Live.

Gemini 3.8 Live and 3.8 Live Extended Thinking are Google's audio-to-audio voice models with background tool calls. Benchmarks, pricing and how to build.

AI voice fraud needs only three seconds of audio to clone a voice, and detection has failed. The defenses that work and what voice tech builders should change.

The Realtime API uses WebSockets for two-way voice interaction with function calling and stateful conversations. Here is how to set it up and build on it.
Keep exploring

New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
Explore 840 topics
Browse All Topics