Eleven v3
Eleven v3 is a text to speech model that generates expressive, emotionally rich speech controlled through inline audio tags for tone, delivery, laughter, whispers, and other non verbal sounds. It supports multi speaker dialogue generation for natural sounding conversations and produces speech in over 70 languages, with major accuracy gains over its Alpha release in reading numbers, symbols, and specialized notation correctly.
- Type
- Audio
- Weights
- Closed
- Downloads
- 21
- Likes
- 2
- Pipeline
- text generation
- License
- apache-2.0
Model hub
bizbots/eleven-v3
- Repo
- bizbots/eleven-v3
- Library
- peft
- Access
- Public
Technical tags and languages
Related tools
1
More from ElevenLabs
9
-
Eleven Flash v2.5
Audio
AI model by ElevenLabs
-
Eleven Multilingual
Audio
AI model by ElevenLabs
-
Eleven v3 alpha
Audio
Eleven v3 (alpha) is ElevenLabs’ next-gen speech model for lifelike TTS, dubbing, and speech-to-speech. It ad…
-
ElevenLabs Scribe
Audio
AI model by ElevenLabs
-
Music v2
Multimodal
Music v2 is ElevenLabs’ closed-source AI music model for generating, editing, remixing, and inpainting full s…
-
Music v2.5
Audio
Music v2.5 is ElevenLabs AI music generation model, the new default on the ElevenMusic platform. It creates m…
-
Scribe v2 Realtime
Audio
Scribe v2 Realtime is a low-latency speech model for live transcription and captioning. It streams partial an…
About ElevenLabs
1
ElevenLabs provides AI voice generation, speech synthesis, dubbing, and conversational-agent technology.
Tools using Eleven v3
16
- AI composes the story—you direct
- Cinematic Slideshow Studio v1
- Slideshows
- cinematicslideshowstudio.com
- Free + from $14.00/mo
- 768 2 1.0
- Video, design & audio from one idea
- Dreamtide v1
- Ads
- www.dreamtide.co
- Spencer H 🛠️ 1 tool 🙏 3 karma
- Sep 15, 2026
- @Dreamtide
- 🇺🇸 United States
- Free + from $20.00/mo
- 423 2 5.0