infinite-livestream
infinite-livestream
An end-to-end reference implementation where Twitch or YouTube prompts become expanded scenes, generated clips, and a continuous RTMP broadcast.
An open-source chat-driven AI video system for Twitch or RTMP, using LTX Video locally or through fal, with a dashboard and metrics.
View repository ↗infinite-tv
It shows a practical route beyond H3 Max for building a chat-steered AI broadcast system.
This reference widens the model beyond H3 Max by showing how local LTX Video or fal can plug into a chat-driven Twitch or RTMP system.
This is source code, not a hosted channel. You need to inspect, configure, and deploy it with your own keys and runtime before anything can broadcast.
Inspect the dashboard and provider configuration, then run the repository with the runtime and streaming services it expects. It is a build reference, not a public channel.
Best for: Developers comparing local and hosted video-generation paths for AI live streaming.
Access note: Open source; self-hosting and provider configuration required.
Open-source repository from the supplied source list. It is a deployable system, not a turnkey public channel.
infinite-livestream
An end-to-end reference implementation where Twitch or YouTube prompts become expanded scenes, generated clips, and a continuous RTMP broadcast.
LiveTalking
A digital-human conversation engine supporting several lip-sync backends, interruption handling and WebRTC, RTMP or virtual-camera output.
WorldCupVoice
An open-source project that watches an Agora RTC live feed, generates context-aware voice commentary, and publishes the AI audio back to viewers with a transcript.