Eleven v3 (alpha) - The most expressive Text to Speech model ever
Supporting 70+ languages, multi-speaker dialogue, and audio tags such as [excited], [sighs], [laughing], and [whispers]. Now in public alpha and 80% off in June.
Conversational AI 2.0 From ElevenLabs - Powering the next-gen of smart, trusted voice agents
A major evolution of our platform, empowering the creation of the most advanced and trustworthy voice agents. Just five months since our last release, this update brings powerful improvements and full enterprise readiness—ushering in a new era.
SB-1 Infinite Soundboard by ElevenLabs - Custom soundboard creator
Make your own custom soundboard using any sound effect you can think of. Perfect for gaming, streaming, Discord and more
I'm the ElevenLabs CEO - what do you want to do with voice AI but can't? (AMA)
Hi Everyone!
Solving AI audio end-to-end means tackling both generation and understanding - from text-to-speech to speech-to-text and everything in between. At ElevenLabs, we re working on breakthroughs in AI audio that bridge research and real-world use.
Ask me anything about what we re building, the challenges of scaling AI speech models, and where this space is headed. Also keen to hear what you ve built with ElevenLabs!
ElevenLabs Text to Bark - The world's first AI-powered TTS model for dogs
Talk to your dog with our new AI Pawdio engine. Simply type a message, choose your breed, and our models will convert it into fluent barking. 😀
ElevenLabs Studio - Structure, edit, and generate long-form audio with precision
Studio, ElevenLabs’ AI longform text-to-audio editor for creators and storytellers is now free for everyone! Create audiobooks, voiceovers, and podcasts with new upgrades like pacing control, auto-assigned voices, and GenFM for AI-driven podcast creation.
Voice Isolator by ElevenLabs - Free voice isolator and background noise remover
Remove unwanted background noise and extract crystal clear dialogue from any audio to make your next podcast, interview, or film sound like it was recorded in the studio.
ElevenLabs Scribe - The most accurate Speech to Text model
It outperforms Gemini 2.0 and Whisper v3, setting new benchmarks in accuracy. Leading in English, Spanish, Italian, and more, it supports 99 languages, speaker diarization, character-level timestamps, and non-speech events like laughter.
Voice Design by ElevenLabs - Generate a custom voice based on a text prompt
Create a unique voice to use with our free text to speech generator for voiceovers, games, audiobooks and more.
Elevenstudios by ElevenLabs - Fully managed video and podcast dubbing
Fully managed video and podcast dubbing. Expand your reach to global audiences by translating your content for foreign audiences. Let our AI and bilingual dubbing experts do the work for you.