ElevenLabs released Eleven v4 and Eleven v4 Turbo text-to-speech models. Eleven v4 uses a new architecture for more emotive, controllable speech. It supports 90+ languages and 17,500+ voices. Professional Voice Clones are supported again after being absent in v3. Audio tags like laughs or whispers are followed more reliably. Context stitching keeps long-form audio consistent. Regenerations retain the same speaker identity. Eleven v4 Turbo is a low-latency variant for real-time use. It has ~100 ms median inference latency and ~150 ms time to first speech. Both models are available via apps, API, and agents. They support bidirectional streaming for agent loops. Professional Voice Clones work identically across both models. The models are available now.
What changed
Eleven v3 lacked Professional Voice Clone support and had less reliable audio tag following.
What it unlocks
Creating expressive, controllable speech with layered emotion, audio events, and immersive soundscapes in real time.
- 90+ languages
- 17,500+ voices
- 10,000 characters per generation
- ~100 ms median inference latency
Sources