lucataco/xtts-v2

Replicate Explore Models
speech-synthesis open-source foundation-model text-to-speech multilingual

Summary

XTTS-v2 is an open foundation speech model by Coqui that supports multiple languages for text-to-speech synthesis, with recent additions like Hindi support.

lucataco / xtts-v2
Original Article
View Cached Full Text

Cached at: 09/14/26, 02:20 AM

# lucataco/xtts-v2 โ€“ Replicate Source: [https://replicate.com/lucataco/xtts-v2](https://replicate.com/lucataco/xtts-v2) ## Readme This model expects that you use at least 6 seconds of audio *Note: Dont include spaces in your input audio file name* ## About XTTS\-v2 the Open, Foundation Speech Model by Coqui ๐Ÿธ Language Settings: English: en ๐Ÿ‡บ๐Ÿ‡ธ French: fr ๐Ÿ‡ซ๐Ÿ‡ท German: de ๐Ÿ‡ฉ๐Ÿ‡ช Spanish: es ๐Ÿ‡ช๐Ÿ‡ธ Italian: it ๐Ÿ‡ฎ๐Ÿ‡น Portuguese: pt ๐Ÿ‡ต๐Ÿ‡น Czech: cs ๐Ÿ‡จ๐Ÿ‡ฟ Polish: pl ๐Ÿ‡ต๐Ÿ‡ฑ Russian: ru ๐Ÿ‡ท๐Ÿ‡บ Dutch: nl ๐Ÿ‡ณ๐Ÿ‡ฑ Turksih: tr ๐Ÿ‡น๐Ÿ‡ท Arabic: ar ๐Ÿ‡ฆ๐Ÿ‡ช Mandarin Chinese: zh\-cn ๐Ÿ‡จ๐Ÿ‡ณ ## Changelog 11/28/23 \- Added Hindi support Model createdover 1 year ago

Similar Articles

Zyphra/ZONOS2

Hugging Face Models Trending

ZONOS2 is a new text-to-speech model from Zyphra trained on over 6 million hours of multilingual speech, offering high-quality voice cloning and low latency using a mixture-of-experts architecture. It supports 30+ languages and includes a high-performance inference server.

kyutai-labs/pocket-tts

GitHub Trending (daily)

Kyutai releases Pocket TTS, a lightweight text-to-speech model that runs efficiently on CPUs with 100M parameters, low latency, and voice cloning, supporting multiple languages.