Text-to-speech model
Eleven v4
Eleven v4 is a text-to-speech model from ElevenLabs, released on 28 September 2026 with a low-latency variant, Eleven v4 Turbo. Built on a new architecture, it is designed to interpret tone, pacing and emotion, supports more than 90 languages, inline audio tags and voice cloning, and is available in ElevenAgents, ElevenCreative and the ElevenLabs API.
Last reviewed 28 Oct 2026 · by ElevenLabs
Facts at a glance
| Developer | ElevenLabs |
|---|---|
| Released | 28 September 2026 source |
| Model IDs | eleven_v4 and eleven_v4_turbo source |
| Languages | 90+ source |
| Character limit per request | 10,000 characters (about 10 minutes of audio) for eleven_v4 source |
| Turbo latency | About 100 ms median inference latency; about 150 ms median time to first speech source |
| Instant voice clone input | 10 seconds of audio source |
| API access | Text to Dialogue API (v4) and Text to Dialogue websocket (v4 Turbo) source |
What Eleven v4 is used for
ElevenLabs positions Eleven v4 for audiobooks, character voiceovers in games and animation, dubbing and multilingual projects, and Eleven v4 Turbo for real-time voice agents in support, healthcare and gaming. Users can direct delivery in natural language or with inline tags such as [laughs] or [light rain]. The model also supports Professional Voice Clones and improved IPA phoneme handling for custom pronunciations.
Questions people ask
- What is the difference between Eleven v4 and Eleven v4 Turbo?
- Eleven v4 is the highest-quality model for expressive speech. Eleven v4 Turbo is the low-latency variant for real-time agents, with a median inference latency of about 100 ms, according to ElevenLabs.
- How many languages does Eleven v4 support?
- More than 90, according to ElevenLabs' model documentation.