# Eleven v4

elevenlabs, released 2026-09-28

**Verdict: conditional.** Conditional. Eleven v4 is ElevenLabs' long-form text-to-speech model (id eleven_v4), covering 90+ languages with multi-speaker dialogue and voice cloning, and accepting up to 10,000 characters per request. The deciding caveat is price: $0.022 per 1K characters is a 72%-off promo that ends Oct 12 against a $0.08 list rate, and the quality claims are ElevenLabs' own, untested by us. Suits teams producing content and long-form audio who budget at list price. Last verified 2026-10-02.

## Pricing

- Input: $0.08 / 1K characters
- Output: Billed per character (single rate)
- Context: List $0.08 / 1K chars; 10K char limit

## Strengths

- Content creation and long-form audio: the changelog routes eleven_v4 to the Text to Dialogue API for that use, and the models page gives a 10,000-character limit, about 10 minutes of audio
- Multi-speaker dialogue: the models page lists support for natural multi-speaker dialogue
- Voice cloning: the models page describes high-fidelity cloning with speaker preservation across long text generations
- Multilingual output: 90+ languages per the models page
- Real-time agents and interactive apps: ElevenLabs points those to eleven_v4_turbo, and the models page lists no latency figure for eleven_v4
- Single requests over 10,000 characters, which exceed the stated limit
- Budgets built on the launch promo rate: the promo has ended and the pricing page shows $0.08 per 1K characters as the price

## Sources

- [ElevenLabs docs changelog, Eleven v4 and v4 Turbo](https://elevenlabs.io/docs/changelog/2026/9/28)
- [ElevenLabs API pricing](https://elevenlabs.io/pricing/api)
- [ElevenLabs docs: models overview](https://elevenlabs.io/docs/overview/models)
- [ElevenLabs docs changelog, 5 October 2026](https://elevenlabs.io/docs/changelog)

Canonical: https://neomanex.com/models/eleven-v4