Tag with "Speech Synthesis"

July 1

Qwen-TTS Expands Support to Three Chinese Dialects

2025年7月1日

The latest update of Qwen-TTS introduces support for Beijing, Shanghai, and Sichuan dialects, enhancing its text-to-speech capabilities. Trained on over 3 million hours of data, the model now offers seven voice tones and improved naturalness in speech synthesis. Developers can integrate these features via API.

DAMN

2025

June 5

Bland AI's TTS Engine Achieves Breakthrough in Voice Cloning

2025年6月5日

Bland AI has unveiled its Bland TTS engine, a revolutionary voice synthesis technology capable of cloning any human voice with just a short audio sample. The system also supports contextual emotion adaptation and sound effect generation, promising transformative applications across industries.

DAMN

2025

May 16

China's MiniMax Voice Model Outperforms Global Rivals

2025年5月16日

Chinese AI firm MiniMax has topped international speech synthesis benchmarks with its new 'Speech-02' model, surpassing competitors like OpenAI and ElevenLabs in quality while costing just a quarter of rival solutions.

DAMN

2024

November 24

Meta Unveils SPIRIT LM: An AI Model for Emotional Expression

2024年11月24日

Meta has launched SPIRIT LM, an open-source multimodal language model that integrates text and speech capabilities. This innovative model not only recognizes and generates speech but also expresses emotions, marking a significant advancement in AI technology.

DAMN

AI DAMN

Tag with "Speech Synthesis"

Tags

July 1

Qwen-TTS Expands Support to Three Chinese Dialects

June 5

Bland AI's TTS Engine Achieves Breakthrough in Voice Cloning

May 16

China's MiniMax Voice Model Outperforms Global Rivals

November 24

Meta Unveils SPIRIT LM: An AI Model for Emotional Expression