ElevenLabs Releases Eleven v4: New Architecture Supports Emotional Multi-Speaker Dialogue and Low-Latency Agent Interaction
ElevenLabs released its most expressive text-to-speech model, Eleven v4, alongside the low-latency Eleven v4 Turbo on September 30, 2026. The new models feature a novel architecture designed to interpret tone, pacing, and emotion for more performative speech generation, with significant improvements in multi-speaker dialogue naturalness. v4 Turbo targets real-time agents with approximately 100ms median latency. The update also enhances audio tag adherence and support for over 90 languages, with notable gains in Japanese, Brazilian Portuguese, and Chinese.
ImportanceMaterialEvidenceE2 unreplicatedWrite-upQuick
ElevenLabs has released its latest text-to-speech models, Eleven v4 and Eleven v4 Turbo. According to the official video description, v4 is built on an entirely new architecture that interprets tone, pacing, emotion, character, and context to generate speech that feels performed. It understands who is speaking and what just happened, simulating the overlap, timing, and reactive energy of real conversations in multi-speaker scenarios, even without explicit audio tags.
The release includes two models based on the same research: Eleven v4 is designed for produced content such as narration, character work, voiceover, and dubbing. Eleven v4 Turbo is the low-latency version tailored for voice agents, live assistants, and interactive experiences, running at around 100 ms median latency while maintaining the same expressive range and bidirectional input streaming capabilities.
Technically, v4 follows audio tag sequences far more reliably than v3, including stacked tags in a single line. Voice cloning stability has improved, with speaker identity holding across long-form work, regenerations, and dialogue turns. Enhanced context stitching ensures regenerated lines fit seamlessly into surrounding chapters, which is critical for audiobooks. Eleven v4 covers over 90 languages, with the strongest gains over v3 reported in Japanese, Brazilian Portuguese, Mandarin, and Cantonese, plus better International Phonetic Alphabet (IPA) support for tricky pronunciations.