AI voice assistant

EMOVA (EMotionally Omni-present Voice Assistant) is a multi-modal language model that enables end-to-end speech processing while maintaining leading visual-linguistic performance. The model enables emotionally rich multimodal dialogue through a semantic-acoustic decoupled speech tokenizer and achieves state-of-the-art performance on visual-linguistic and speech benchmarks.

Qwen2 Audio Instruct Demo is an interactive demonstration website based on audio commands. It uses the latest artificial intelligence technology to allow users to interact with web pages through voice commands. This technology not only enhances the user experience, but also provides easier access for people with disabilities. The product background information includes its development team and technical support, and the price is positioned as a free trial, mainly for user groups interested in artificial intelligence interaction.

Friend is a leading open source AI wearable device that provides automatic, high-quality real-time transcription services for meetings, chats, and voice memos by connecting to mobile devices. It has real-time AI audio processing capabilities, low-power Bluetooth technology, and open source software design, allowing users to easily access and contribute code. With its portability, practicality and open source nature, this product provides an innovative solution for users who need to efficiently record and manage conversation content.

FRIEND NECKLACE is an open source wearable AI assistant with personalized AI dialogue and feedback functions. It is a smart device that integrates AI notes, reminders, suggestions and other functions. The product is completely open source, and all data is stored on the user's mobile phone, ensuring data privacy and security.

MiGPT is a project that realizes smart home voice control by combining Xiaoai speakers with the intelligent understanding capabilities of ChatGPT. It not only supports device automation, but also enables smart home devices to respond to user instructions more intelligently and thoughtfully through technologies such as role playing, streaming response, and long and short-term memory. MiGPT supports two startup methods: Docker and Node.js, and users can choose according to their own needs.

AI Smart Speaker is a browser plug-in that can automatically read and record ChatGPT replies and selected text. You can download the recording as an MP3 format file. The speakerphone comes with a variety of features and benefits, including automatically reading chat replies, recording selected text, supporting downloading of MP3 files, and more. Please refer to the official website for pricing details.