# ElevenLabs releases Eleven v4 and Eleven v4 Turbo

The models support over 90 languages and inline performance tags, with the Turbo variant delivering approximately 100 ms median inference latency.

- Inline tags allow users to direct emotion, pacing, style, sound effects, and pronunciation via IPA support.
- Instant Voice Clones generate voice models from 10 seconds of sample audio.
- Language coverage spans 90+ languages, including Cantonese, Mongolian, and Odia.
- Eleven v4 is available across ElevenAgents, ElevenCreative, and ElevenAPI, with temporary promotional API pricing of $22 per 1M characters for v4 and $11 for v4 Turbo.

## Why it matters

Developers building realtime voice agents can access lower latency and granular prompt control over emotion and pronunciation.

## Sources

- [ElevenLabs: ElevenLabs releases Eleven v4 and Eleven v4 Turbo](https://x.com/ElevenLabs/status/2104572127617994917)

---

Summarized by dstilled on 2026-09-28. https://dstilled.ai/story/1cc1101c-f5c5-47f1-aa9f-34d2336e66c8