Eleven v4 Turbo
Eleven v4 Turbo is the realtime variant of the v4 architecture. ElevenLabs developed it alongside ElevenAgents, with the same broad multilingual scope as v4.
Interactive voice
The API streams speech for agents and interactive applications. It is a speech-generation model; a full conversational agent also needs recognition, reasoning and turn-taking.ElevenLabs: September 2026 model and API changesElevenLabs API introduction and model specifications
Practical guidance. Use the server figure as one part of a conversation budget. Measure the complete pause between the user’s last word and the first audible reply.ElevenLabs latency measurement method
Specifications & access
| Detail | Value and conditions |
|---|---|
| Launch date | |
| Access | API, Provider product |
| Model identifiers | eleven_v4_turbo |
| API route | Text to Dialogue WebSocketElevenLabs: September 2026 model and API changes |
| Server latency | About 100 ms median, for warm voices; excludes network and application timeElevenLabs latency measurement method |
Related models
- Eleven v4
ElevenLabs · Eleven speech
Speech model for expressive narration, consistent character voices and multi-speaker dialogue.
Launch date API · Provider product - Eleven Flash v2.5
ElevenLabs · Eleven Flash
Multilingual speech model designed for short response delays.
Launch date API · Provider product - Eleven v3 Conversational
ElevenLabs · Eleven speech
Realtime v3 speech model for directed delivery in voice agents.
Launch date API · Provider product