Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Excited to introduce Fish Speech 1.4 - now open-source and more powerful than ever! 🎉 Our mission is to make cutting-edge voice tech accessible to everyone. What's new: - Trained on 700k hours of multilingual data (up from 200k) - Now supports 8 languages: English, Chinese, German, Japanese, French,...

149,977 Aufrufe • vor 1 Jahr •via X (Twitter)

10 Kommentare

Profilbild von AT
ATvor 1 Jahr

Not bad, but we need to add Russian.

Profilbild von Fish Audio
Fish Audiovor 1 Jahr

Plan to add in next major release.

Profilbild von Pranay Suyash
Pranay Suyashvor 1 Jahr

any indic languages in the pipeline?

Profilbild von Udit Goenka
Udit Goenkavor 1 Jahr

Just tested...Instant voice clone requires some work, specially with Indian English accept. The sample for training data is too less. Other than that, great work on open sourcing it!

Profilbild von ChatBoo - AI Companion
ChatBoo - AI Companionvor 1 Jahr

Can I confirm the license? GitHub and HF both say non commercial. But your post uses the term open source which has a strong meaning

Profilbild von ryu
ryuvor 1 Jahr

Congrats!

Profilbild von ChatBoo - AI Companion
ChatBoo - AI Companionvor 1 Jahr

Does your API offer streaming? What is the expected latency? Am I correct in understanding that your pricing is $15USD per million bytes?

Profilbild von Fish Audio
Fish Audiovor 1 Jahr

Yes, the API does support streaming, the current E2E latency is around 400ms, we are working with our providers to further cut-down network latency.

Profilbild von Tonado
Tonadovor 1 Jahr

正好需要一个,替代剪映会员的克隆声音功能,剪映要一个月要59来着,而且只给很有限的点数

Profilbild von UnShelledSec
UnShelledSecvor 1 Jahr

When portuguese?

Ähnliche Videos