ElevenLabs ships Eleven v4: steerable speech with per-character performance and soundscapes
korymath · x · 2026-09-29
ElevenLabs released Eleven v4, a new speech architecture enabling more realistic and controllable voice: you can direct both a character's performance and the soundscape around them, with voice effects like "cheap microphone." A dev who has worked on realistic human laughter vouched for the quality.
More from Multimodal
- Flatbed debuts: an AI-native video editor where every asset is individually promptable — rchardkovacs · 2026-09-29
- One Image to a Walkable World: Hyper3D + GPT-6 Rebuilds Scenes in Three.js — Scobleizer · 2026-09-29
- Light Field Primitives: differentiable primitives replace dense ray databases for real-time novel view synthesis — zhenjun_zhao · 2026-09-29
- Face/Head Swap Workflow v2.0 released with full video tutorial — feroszy · 2026-09-29
- Filming a four-character restaurant scene with MiniMax H3: workflow advice wanted — Complete-Box-3030 · 2026-09-29
- Two reusable prompts: p5.js story trailers and news-meme YouTube explainers — dotey · 2026-09-29