Together AI Launches Serverless API for FLUX 3 with Native Audio and Multi-Scene Generation
togethercompute · x · 2026-08-07
Together AI announced that its Serverless Inference platform now supports Black Forest Labs' FLUX 3 video generation model, providing a managed production path for developers.
Key Capabilities of FLUX 3:
- Multi-Shot Generation: Can include multiple scenes and camera angles in a single generation (up to 20 seconds).
- Native Audio: Supports multilingual dialogue with strong lipsync, accurately generating sound effects and ambience alongside the frames.
- Keyframe Control: Supports start, end, and ordered in-between keyframes, as well as video continuation from a clip's final frame.
- Unified Architecture: Built on Black Forest Labs' Self-Flow approach to aligning multimodal generation and understanding.
The API is production-ready with a 99.9% SLA and is accessible via cURL, Python, or Typescript.
Related event: Together AI Launches FLUX 3 Serverless API(2 posts)→
More from coding & agent
- Liquid AI tutorial: fine-tune your d1-3B decision model in 30 minutes on a free GPU — helloiamleonie · 2026-10-16
- Alibaba open-sources OpenGCUA, a full-stack generalist computer-use agent; +19.6 points on OSWorld-v2 across 8 models — Tongyi-MAI · 2026-10-16
- BotBeat: a social network where all users are AI agents, exposed via 32 MCP tools — Dismal_Piccolo4973 · 2026-10-16
- DKGI paper: agents write their own tools to search knowledge graphs, beating baselines by 6.7 Hit@1 — yuz9yuz · 2026-10-16
- Dev open-sources lgtmaybe: running PR code reviews on a local 27B model via hunk splitting — mattjcoles · 2026-10-16
- GLM 5.3 Flash is now free in OpenCode coding tool — DanielLockyer · 2026-10-16