Oct 30, 02:17 PM

Hedra Launches Voice Cloning for Paid Users; MaskGCT TTS Model with Zero-Shot Voice Cloning Supports Chinese & English

Hedra has launched a new voice cloning feature that allows paid users to record a voice clip and clone their voice for use with Hedra characters. Users can upload or generate an image, enabling their characters to speak in their own voice. Additionally, a new open-source text-to-speech model named MaskGCT has been introduced, available on Hugging Face. This model boasts features such as zero-shot voice cloning, emotional text-to-speech capabilities, and support for bilingual synthesis in Chinese and English. MaskGCT has been trained on 100,000 hours of data and offers long-form and variable speed synthesis options.

#Hedra #MaskGCT #Hugging Face #Chinese #English

Written with ChatGPT (GPT-4o mini).

Sources

Sylvain Filoni@fffiloni
2 years ago
I've added the MaskGCT TTS @gradio API to the Echo Mimic Space, so you can directly clone your voice before generating portrait generation 🤗 Try it —› https://t.co/vSWUt0lbEL https://t.co/y4caaAitVz https://t.co/p1jOHm3UBM
Vlad Ruso PhD@vlruso
2 years ago
MaskGCT: A New Open State-of-the-Art Text-to-Speech Model https://t.co/WzdyYk4req #MaskGCT #TextToSpeech #AItechnology #OpenSourceAI #VoiceCloning #ai #news #llm #ml #research #ainews #innovation #artificialintelligence #machinelearning #technology #deeplearning @vlruso https://t.co/rkoSKvjewY
Marktechpost AI Research News ⚡@Marktechpost
2 years ago
MaskGCT: A New Open State-of-the-Art Text-to-Speech Model MaskGCT is a new open-source, state-of-the-art TTS model available on Hugging Face. It brings several exciting features to the table, such as zero-shot voice cloning and emotional TTS, and can synthesize speech in both… https://t.co/hXkk8z9pOT

Hedra Launches Voice Cloning for Paid Users; MaskGCT TTS Model with Zero-Shot Voice Cloning Supports Chinese & English

Sources

Additional media