Audio
GA
Proprietary
Eleven v3
Expressive text-to-speech and dubbing
Release2025-06
Context—
Max output—
ParametersUndisclosed
Local / VRAMAPI only
LicenseProprietary
Overview
Eleven v3 is a model in the Audio category from ElevenLabs. It was released in 2025-06. The vendor is based in US. Best for: Expressive text-to-speech and dubbing.
Notes: Positioning from the vendor site; specs, access and pricing can change — verify before production use.
Strengths
- Natural voices
- Voice cloning
- 70+ languages
Limits
- Credit based
- Cloning consent rules
Specifications
| Vendor | ElevenLabs |
|---|---|
| Category | Audio |
| Release | 2025-06 |
| Status | GA |
| License | Proprietary |
| Commercial use | Not specified |
| Input modalities | Text |
| Output modalities | Audio |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | No |
| API access | Yes |
| Pricing | Free tier / Starter $5+/mo / API |
| Confidence | Medium |
| Vendor country | US |
| Vendor type | Media lab |
Pricing & hardware
Free tier / Starter $5+/mo / API
API-only: local GPU memory is not applicable. API access is available.