Q
Qwen3 TTS
21
Open-source TTS model with 12Hz audio generation and voice cloning capabilities
Open Sourceopen-source
About
Qwen3 TTS is a 1.7B parameter text-to-speech model offering high-quality 12Hz audio synthesis with custom voice cloning features. With 831K downloads on HuggingFace, it enables developers to generate natural-sounding speech while preserving speaker characteristics. Ideal for applications requiring personalized voice generation without API dependencies.
Details
| Modality | text |
| Release Date | Feb 20, 2026 |
| API Available | Yes |
| Hosting | api |
Tags
open-weightaudioself-hostedfine-tunableapi
Quick Info
- Organization
- Qwen
- Pricing
- Free (self-hosted)
- Free Tier
- Yes
- Popularity
- 55/100
- Updated
- Feb 20, 2026
Also in AI Models
C
Claude Opus 4.6
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional...
Commercialpaid
Anthropic$5.00/1M input tokens
C
Claude Sonnet 4.6
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier per...
Commercialpaid
Anthropic$3.00/1M input tokens
G
Gemini 3 Flash
Google DeepMind's latest fast and capable multimodal AI model
Commercialfreemium
Google DeepMindFree tier available / $0.50/1M input tokens (Flash)