Eleven v4 demo goes live: pick emotions per word, replay sentences with feeling
NevFlynn · x · 2026-09-29
An ElevenLabs team member shared the playable demo for Eleven v4, the company's fastest and most emotive voice model to date.
The demo lets you steer tone with audio tags like [excited], [playful], and [amazed], click individual words to set their emotion, replay sentences, and try a built-in voice chat — all wrapped in a 3D animated page that visualizes the model's emotional range.
More from Multimodal
- Minimax H3 Video Imagines Superman as a Saiyan in Fan-Made Crossover — rogerro007 · 2026-09-29
- New video benchmark ranks 15 text-to-video models — chancemehmu · 2026-09-29
- P-Video-2-Pro jumps 19-22 spots, top-6 on DesignArena for both T2V and I2V — guennemann · 2026-09-29
- Largest Open-Source Human Video Preference Dataset Released: 300K Annotations, 15 SOTA Models Ranked — _akhaliq · 2026-09-29
- Professor generates an immunology explainer video with Claudia 5.5 in two 2-hour passes, zero manual concept edits — ramos_casals · 2026-09-29
- Why anime creators still pick SDXL/Pony over Flux — plus a free tag prompt generator — vtatv · 2026-09-29