GoKawiilElevenLabs launches v4 and v4 Turbo speech models with 90-language support
ElevenLabs released two new speech models, v4 and v4 Turbo, adding expanded expression control, faster voice cloning from just 10 seconds of audio, and support for over 90 languages, up from 70. The company said quality improved most notably in Japanese, Brazilian Portuguese, Mandarin and Cantonese, and the new models offer lower latency aimed at voice agent applications.
GoKawiil's interpretation of the reporting above, not reported fact.
Lower latency and better multilingual support could make ElevenLabs more competitive for enterprise voice-agent deployments, an area the company says already accounts for over 55% of its business. The upgrade comes as rivals like Cartesia, Deepgram and Google push into expressive speech AI, suggesting ElevenLabs is racing to defend its position after raising $500 million from Sequoia this year.
- ElevenLabs v4 and v4 Turbo support over 90 languages, up from 70 in the previous version.
- Voice cloning now requires just 10 seconds of audio, with expanded inline expression tags.
- Lower latency targets enterprise voice agents, which already make up more than 55% of ElevenLabs' business.
Source: techcrunch.com — Ivan Mehta, 2026-09-28
Published there as: “ElevenLabs’ new v4 speech model supports more expression control and 90 languages”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.