Model · ElevenLabs · Text-To-Speech
ElevenLabs Eleven v3
ElevenLabs' flagship expressive TTS (Eleven v3). The benchmark for natural-sounding speech and voice cloning across 70+ languages; Flash v2.5 covers low-latency use.
- Modality
- Text-To-Speech
- License
- Proprietary (Proprietary)
- Released
- February 2, 2026
- Last verified
- September 8, 2026
- Runs locally
- No
Strengths
- Best-in-class voice naturalness and expressive delivery (v3)
- Voice cloning from short samples
- 70+ languages; Flash v2.5 (~75ms) for real-time/low-latency use
Weaknesses
- Closed weights — fully API-bound
- Voice cloning brings consent and ethics considerations
Try it
| Where | Type | Notes |
|---|---|---|
| ElevenLabs API | hosted-api | API key required, free tier |
| ElevenLabs Studio | product | Web UI |
Official sources
- Model docs docs
- API reference docs
Change log
- — Dropped Turbo v2.5 from purpose and strengths — ElevenLabs' models page now marks Eleven Turbo v2.5 and Turbo v2 as deprecated, 'outclassed by Flash models', with eleven_flash_v2_5 as the replacement. Eleven v3 itself verified current; no v4 exists.
- — Link fix: promoted the models overview (elevenlabs.io/docs/overview/models) to the primary docs link. The API reference was the only docs link, and it does not enumerate models — which made it a poor verification source. Kept as a secondary link.
- — Updated from Multilingual v2 to Eleven v3 (GA 2026-02-02), 70+ languages. Multilingual v2 remains available but is no longer the flagship.
- — Initial entry.
Esc