neonbjb/tortoise-tts
Tortoise is a high-quality multi-voice text-to-speech system focused on realistic prosody and intonation, offering various usage modes and advanced performance optimizations.
Awesome AI Agents › Audio & Voice Assistants
2noise/ChatTTS
ChatTTS is a state-of-the-art generative text-to-speech (TTS) model specifically designed for daily dialogue and conversational scenarios, such as those involving large language model (LLM) assistants. It supports multiple languages, including English and Chinese, with plans to expand to more languages. The model excels in producing natural, expressive, and interactive speech synthesis, making it highly suitable for dialogue-based applications. One of the key features of ChatTTS is its fine-grained control over prosodic elements like laughter, pauses, and interjections, which enhances the naturalness and expressiveness of the generated speech. This capability allows for more human-like and engaging conversations. ChatTTS outperforms many open-source TTS models in terms of prosody quality, supported by pretrained models available for research and development. The model has been trained on a vast dataset comprising over 100,000 hours of Chinese and English audio data, with the open-source version on HuggingFace offering a 40,000-hour pretrained model. The project includes algorithm infrastructure and simple examples, with extended end-user products maintained by the community in a separate repository. ChatTTS is released under the AGPLv3+ license for code and CC BY-NC 4.0 for the model, emphasizing academic and research use only. The developers have implemented measures to prevent misuse, such as adding noise during training and compressing audio quality. The repository provides comprehensive installation instructions, including optional components for enhanced performance on NVIDIA GPUs, and offers both command-line and web UI interfaces for easy use. Advanced usage includes speaker sampling and manual control over speech synthesis parameters, enabling customization at both sentence and word levels. The project encourages responsible and ethical use of the technology and provides multiple channels for community support and formal inquiries.
https://github.com/2noise/ChatTTS
Also in Audio & Voice Assistants
livekit/agents
LiveKit Agents is an open-source framework for building real-time voice AI agents with integrated speech-to-text, large language models, text-to-speech, and telephony capabilities.
openinterpreter/01
01 is an open-source voice interface platform that enables natural language voice control across desktop, mobile, and ESP32 devices, offering extensive customization and hardware support.
ahmedeltaher/Android-MVVM-Architecture-Android-Voice-AI-SDK
A reusable Android library in Kotlin that adds a full voice conversation pipeline to an app, chaining microphone capture, voice activity detection, speech-to-text, an Anthropic Claude response and text-to-speech.
elevenlabs/ui
ElevenLabs UI is a component library built on shadcn/ui that provides customizable React components to help developers build multimodal agent and audio applications faster.
akdeb/ElatoAI
ElatoAI enables real-time AI speech interaction on Arduino ESP32 devices using OpenAI, Gemini, and Eleven Labs AI models with secure websocket communication and a web app for control.
bolna-ai/bolna
Bolna is an open-source end-to-end platform for building voice-first conversational AI agents by orchestrating telephony, speech recognition, language models, and speech synthesis technologies.
joinly-ai/joinly
joinly is a self-hosted MCP server that lets an AI agent join Google Meet, Zoom or Teams calls in a browser, listen through speech-to-text and reply by voice or chat in real time.