ModelSpeech & Audio AIvv2

XTTS-v2

by Coqui AI · open-source · Last verified 2026-03-17

XTTS-v2 is Coqui AI's open-source cross-lingual text-to-speech model that achieves high-quality voice cloning from as few as 6 seconds of reference audio and supports 17 languages in a single model. It offers real-time streaming inference, making it a leading open-source choice for applications requiring custom voice synthesis and low-latency output.

https://coqui.ai/blog/tts/open_xtts ↗

C+

C+—Average

Adoption: BQuality: AFreshness: B+Citations: BEngagement: F

Specifications

License: Coqui Public Model License
Pricing: open-source
Capabilities: text-to-speech, voice-cloning, multilingual-tts, real-time-streaming, emotion-control
Integrations: huggingface, local-inference
Use Cases: voice-cloning, audiobook-narration, virtual-assistants, game-characters, accessibility
API Available: Yes
Parameters: ~500M
Context Window: N/A
Modalities: text, audio
Training Cutoff: 2023
Tags: text-to-speech, voice-cloning, multilingual, open-source, coqui-tts
Added: 2026-03-17
Completeness: 100%

Index Score

59.6

Adoption

Quality

Freshness

Citations

Engagement

Explore the full AI ecosystem on Agents as a Service