Text to Speech API
Ultra-realistic and low latency speech generation
Build with high-quality, controllable speech generation for real-time and bulk applications. Models optimized for latency, fidelity, and long-form consistency.
Flash v2.5
Our lowest latency speech synthesis model
- Ultra-low latency (~75ms)
- 32 languages supported
- 40,000 character limit
- ~$0.06 per minute
Turbo v2.5
Balanced quality and latency
- Low latency (~250-300ms)
- High quality voice generation
- 32 languages supported
- 40,000 character limit
- ~$0.06 per minute
Multilingual v2
Lifelike, consistent quality speech synthesis model
- Natural-sounding output
- 29 languages supported
- 10,000 character limit
- Designed for long-form generations
- ~$0.12 per minute
Eleven v3
Our most emotionally rich, expressive model
- Dramatic delivery and performance
- 70+ languages supported
- 3,000 character limit
- Multi-speaker dialogue
- ~$0.12 per minute
Control emotion and delivery
Create controllable, expressive speech, layered with emotion, audio events, and immersive soundscapes.
Access 10,000+ voices
Explore an ever-growing collection of expressive, lifelike voices for any use case.
Voice design & cloning
Create in over 30 languages with natural voices, expressive accents, and localized audio tailored to your audience.
Multi-speaker dialogue
Create natural multi-speaker conversations across 30+ languages with expressive, controllable voices.
Audio events and direction
Control delivery with audio tags, timing cues, and narrative direction built into the speech.
Pronunciation dictionaries
Define custom pronunciations to ensure consistent, accurate speech for names and terminology.
“From dubbing Reels in local languages, to generating music and character voices in Horizon, ElevenLabs platform enables global creators, businesses, and enterprises to build with voice, music, and sound at scale.”
“Millions of people learn chess from creators like Hikaru, Levy, and Magnus every day on YouTube and Twitch. Now you can learn from them inside Chess.com in a way that feels immersive, personal, and full of character. Our mission is to build a chess coach that teaches at the right level, welcomes players of every skill level, and demystifies chess while keeping it fun and full of personality. With ElevenLabs and these amazing new voices, we’ve taken a big step toward making that vision a reality.”
“ElevenLabs made it easy for us to quickly bring powerful text-to-speech capabilities to our SDK, allowing Agents to respond in real time with expressive voices to user questions or as feedback to what it’s seeing.”
“Twilio has integrated ElevenLabs’ generative AI voice technology into its CPaaS, enhancing ConversationRelay. This integration allows businesses and developers to create conversational AI voice interactions that sound human, feel expressive, and respond in real time directly from the Twilio CPaaS platform. We at ElevenLabs are excited that Twilio has chosen ElevenLabs to enhance ConversationRelay with the most expressive, human sounding voices available. ”
APIs built for production
.webp&w=3840&q=80)
.webp&w=3840&q=80)
.webp&w=3840&q=80)