Eleven V3
Eleven v3 is a text-to-speech model for videos, audiobooks and media tools. Its higher latency makes it unsuitable for real-time conversation, for which ElevenLabs recommends Eleven Flash v2.5. Summary written by AI Index from ElevenLabs’s own pages.
- Streaming
Prices
1 offering · prices as listed ElevenLabs API (opens in a new tab)
eleven_v3| Conditions/ 1K characters | Character |
|---|---|
| Standard | $0.080 |
Prices from ElevenLabs API pricing (opens in a new tab) (checked Nov 6, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Max input
- 5,000
- Model ID
Cited scores
From third-party leaderboards, not measured by usNo cited leaderboard covers speech synthesis yet. We will cite one when its license allows.
Changes
All changes →- Now priced on ElevenLabs API Character $0.080
- New text to speech model
Sources
- ElevenLabs API pricing (opens in a new tab) elevenlabs.io · checked Nov 6, 2026
- Eleven v3: Most Expressive AI TTS Model Launched (opens in a new tab) elevenlabs.io · checked Nov 6, 2026
- Text to Speech (TTS) API - ElevenLabs (opens in a new tab) elevenlabs.io · checked Nov 7, 2026
- August 20, 2025 | ElevenLabs Documentation (opens in a new tab) elevenlabs.io · checked Nov 6, 2026
- Models | ElevenLabs Documentation (opens in a new tab) elevenlabs.io · checked Nov 6, 2026
ElevenLabs’s official policies: data use, privacy, terms →
ElevenLabs · United States · elevenlabs.io
Related models
Snapshots, the same family and other models from this provider