TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
This is an interface that will offline convert anything pdf document you give it into an interview between two people discussing it.
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
Open-source event-driven AI powered Softphone
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Speech To Speech: an effort for an open-sourced and modular GPT4-o
AI-powered voice calling agent using OpenAI's Realtime API and Twilio
A Full-Duplex Open-Domain Dialogue Agent with Continuous Turn-Taking Behavior
🔊 Text-Prompted Generative Audio Model
Turn detection for full-duplex dialogue communication
True full-duplex acoustic echo cancellation.
This repository is a real-time Voice-to-Voice AI Assistant that enables full duplex conversations using speech and large language models. Built with Python, Streamlit, SpeechRecognition, GTTS, and …
Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
VoxCPM: Tokenizer-Free TTS for Context-Aware Speech Generation and True-to-Life Voice Cloning
A Conversational Speech Generation Model
Optimized Whisper models for streaming and on-device use