Eleven v4
ElevenLabs' new flagship voice model family, ranked No. 1 on Artificial Analysis's Voice TTS Arena, with a low-latency Turbo variant for live calls.
Overview
ElevenLabs released Eleven v4 and Eleven v4 Turbo on September 28, 2026, replacing the Eleven v3 generation at the same list price with a 72% launch discount running through October 12, 2026. Eleven v4 is the quality-focused model and took first place on the Artificial Analysis Provider Voice TTS Arena; Eleven v4 Turbo targets live calls and agent voice loops with about 100ms median inference latency and 150ms median time to first speech. Both models support more than 90 languages, up from 70-plus on Eleven v3.
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- Ranked No. 1 on the Artificial Analysis Provider Voice TTS Arena at launch
- Eleven v4 Turbo variant at ~100ms median inference latency, ~150ms time to first speech, for live calls and voice agents
- 90+ language support, up from 70-plus on Eleven v3
- Launch pricing: v4 at $22/million characters and Turbo at $11/million characters through October 12, 2026 (72% off list)
Use cases
- High-quality narration, dubbing, and voiceover work
- Low-latency voice agents and live phone/call center automation
- Multilingual voice product localization
- Replacing Eleven v3 deployments at the same list pricing
Pricing
List price unchanged from Eleven v3: v4 at $0.022/thousand characters (list $0.08), Turbo at $0.011/thousand characters (list $0.04); launch offer through Oct 12, 2026 at $22/million characters (v4) and $11/million characters (Turbo).
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- 28 Sept 2026
- Record updated
- 29 Sept 2026
- Record last checked
- 29 Sept 2026