ElevenLabs Launches Eleven v4 and 100ms-Latency Turbo Text-to-Speech Models
Summary
ElevenLabs launches Eleven v4 and its Eleven v4 Turbo text-to-speech model, bringing expressive speech to ElevenAgents, ElevenCreative and the API with roughly 100 ms median inference latency and support for more than 90 languages.
Key Points
- ElevenLabs launches Eleven v4 and low-latency Eleven v4 Turbo, its new expressive text-to-speech models, now available in ElevenAgents, ElevenCreative and via ElevenAPI.
- Eleven v4 Turbo delivers median inference latency of about 100 ms and median time to first speech of about 150 ms, and is optimized with the ElevenAgents conversational platform.
- Both models support more than 90 languages, while Instant Voice Clones can capture a voice in high fidelity from 10 seconds of audio and Eleven v4 adds Professional Voice Clone support.