coqui-ai/tts

A Multi-Voice and Prompt-Controlled TTS Engine. EmotiVoice speaks both English and Chinese, and with over 2000 different voices. The most prominent feature is emotional synthesis, allowing you to create speech with a wide range of emotions, including happy, excited, sad, angry and others.

AI voice platform for realistic text-to-speech, voice cloning, dubbing, and conversational voice agents, used by developers and content creators.

Multimodal foundation models for text, speech, video, and music generation

A toolkit for training language models to work with PDF documents in the wild. Online demo: https://olmocr.allenai.org/

Google's free translation service covering 130+ languages, with camera translation, offline packs, and a Gemini-powered live conversation mode.

Text to Video; Image to Video; 4K enhance