ElevenLabs just made its Eleven v3 text-to-speech model generally available across all platforms. The update heavily refines tricky contextual notation like phone numbers, currencies, and sports scores, cutting reading error rates from 15.3% to 4.9% with a 72% user preference over the alpha.
ElevenLabs just rolled out Eleven v3 (alpha) across its API, bringing realistic multi-speaker dialogue and emotional control to developers. The model supports over 70 languages and can handle natural interruptions between unlimited speakers using audio tags. Partners like HeyGen, InVideo, and Poe have already integrated the update.
ElevenLabs just introduced Audio Tags for its Eleven v3 model, letting creators direct the exact timing, rhythm, and emphasis of generated speech. By slipping bracketed cues like [pause], [rushed], or [stammers] right into the script, users can turn monotone readings into nuanced, human-like performances. However, professional voice clones aren't fully optimized for v3 yet.
ElevenLabs just rolled out the alpha release of Eleven v3, its upgraded text-to-speech model featuring heightened emotional awareness and context adaptability. The model supports over 70 languages, up to 5,000 characters per request, and bracketed audio tags for directing whispers and laughter. Why it matters: creators and developers can now generate nuanced, natural character dialogue without hiring voice actors.
