LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

A simple, high-quality voice conversion tool focused on ease of use and performance

A desktop application that uses AI to translate voice between languages in real time, while preserving the speaker's tone and emotion.

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

MooER: Moore-threads Open Omni model for spech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction models along with training and inference code, covering but not limited to end-to-end speech interaction, end-to-end speech translation and speech recognition.

Code for NeurIPS 2023 paper "DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation".

If you've ever had the wish to talk to your AI Waifu using quality characters and voices for character voicing, then I suggest Soul of Waifu. Don't miss the opportunity to touch your dream!

svelte component for using the openai realtime api

💬 "Realtime" voice transcription and cloning using ElevenLabs's API.

Code for the INTERSPEECH 2023 paper "Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models"

Speech to text to speech using Elevenlabs

✨✨Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

Swift SDK for Prototyping AI Speech Generation

Chatter Box is an android app that is capable of Voice, Text, Image Text Translation, and end-to-end chat translation.

A user-friendly interface for ElevenLabs' API with added audio transcription capability.

End-to-End AI Voice Assistant pipeline with Whisper for Speech-to-Text, Hugging Face LLM for response generation, and Edge-TTS for Text-to-Speech. Features include Voice Activity Detection (VAD), tunable parameters for pitch, gender, and speed, and real-time response with latency optimization.

Systems submitted to IWSLT 2022 by the MT-UPC group.

Speech-to-Speech translation dataset for German and English (text and speech quadruplets).

CtrlSpeak is a voice assistant activated with [Control]+Q, listening and responding only when you want.