Audio agents

Audio transcription and alignment library using Google Gemini API for TTS labeling

Instrumentation and telemetry for the Google Gemini Live API via OpenTelemetry

A real-time Gemini API streaming library with FastAPI integration

A Python ASGI Socket.IO server proxying to Gemini Live via WebSockets

A Python package for Gemini Text-to-Speech using the official API.

OpenAI provider adapters for genblaze (Sora, DALL-E, TTS)

Speech-based GPT using Python

Fast GPT-3 client for Windows and Unix that supports both text and speech in any language.

Text-to-speech CLI tool and Python library using OpenAI's TTS API

Gpt powered subtitle translation tool.

A simple script that uses the Groq API to transcribe audio files using the Whisper model

A Voice-Controlled Drone Agent MCP Server

Raspberry Pi MCP Voice Assistant with Qwen-Agent framework

OpenAI TTS + STT voice providers for Kestrel Sovereign

LangChain integration for AgentPhone — telephony tools for AI agents

LangChain integration for CAMB AI - multilingual audio and localization tools

Integration of Sarvam AI platform with LangChain

LangChain integrations for Stardog

A powerful framework for building realtime voice AI agents

Bridge external AI agent frameworks (LangChain, LangGraph, Strands, ADK, custom) to the LiveKit Agent runtime.

gRPC translator for LiveKit Agents Adapter — connect any agent service to LiveKit

LangChain translator for LiveKit Agents Adapter

WebSocket translator for LiveKit Agents Adapter — connect any agent service to LiveKit

Agent Framework plugin for services from Anthropic

Groq inference plugin for LiveKit Agents

LangChain/LangGraph plugin for LiveKit agents

Universal LiveKit plugin for LangGraph workflows with intelligent filtering

Llama Index plugin for LiveKit Agents

LiveKit Agents Plugin for services from Mistral AI

Agent Framework plugin for services from OpenAI

Agent Framework plugin for OpenAI Server-Sent Events TTS API

Agent Framework plugin for OpenAI Server-Sent Events TTS API

Agent Framework plugin for RAG

llama-index tools azure_speech integration

LlamaIndex x ElevenLabs integration

LlamaIndex x Gemini Live integration

LlamaIndex x OpenAI Realtime integration

Train a speech-to-speech model using your own language model

LLM plugin providing access to 75+ AI models through 1min.ai API v2 (chat-with-ai endpoint) with SSE streaming, attachments, AI memory, brand voice, web search, and persistent options

Text-to-speech using the Azure OpenAI TTS API

Transcribe audio using the Groq.com Whisper API

OpenAI-compatible inference server: Llama 3.1 8B + Whisper + Kokoro TTS exposed via ngrok

Library to reduce latency in voice generations from LLM chat completion streams

Full-stack AI chat platform — multi-provider LLM, MCP tools, voice, budget

Llmovoice python library

LLM-powered FFmpeg command assistant

Tools for working with Ollama

Synap memory integration for LiveKit Agents — preload long-term memory, record turns, expose Synap as LLM tools

Natural language to FFmpeg, instantly and privately

A tool to create guided audio meditations (like those found on YouTube but in audio-only form) using OpenAI.

A proxy service converts Minimax TTS API to OpenAI-compatible format

SHAP implementation for multimodal large language models supporting audio and text input.

Moss runtime for LiveKit voice agents - a hot index cache shared across rooms and a one-line attach per call.

CLI tool for deploying Moss voice agents

Moss Voice Agent Manager - Simplified LiveKit agent integration

A library for optimizing audio processing parameters using differential evolution.

l10n_ar_electronic_invoice_storage_rg1361

Local macOS menubar voice assistant powered by MLX Whisper, Ollama, and Kokoro TTS

OpenClaw-inspired AI Agent Framework with NVIDIA Nemotron, Voice, Canvas, Browser Sandbox, and Multi-Channel Support

OpenClaw-inspired AI Agent Framework with NVIDIA Nemotron, Voice, Canvas, Browser Sandbox, and Multi-Channel Support

AgentPhone tools for OpenAI Agents SDK — telephony for AI agents

an openai based game audio translator

A powerful and easy-to-use Python library for generating natural-sounding speech using OpenAI text-to-speech capabilities.

An MCP server integrating with OpenAI TTS (text-to-speech) API

A CLI that provides tts using OpenAI

Free & Unlimited Unofficial OpenAI API Python SDK - Supports all OpenAI Models & Endpoints

A library for real-time text to speech processing using OpenAI API.

Simple CLI wrapper for OpenAI Speech-to-Text API

Speech-to-Text tool using Whisper, PyAudio, and VAD.

Audio-native LLM utilities for Pipecat

Plaud Live Agent SDK - 实时AI助手客户端SDK

OpenAIAudio converter

Python Module for Free ChatGPT TTS

Resp-Agent: A multi-agent framework for respiratory sound diagnosis and generation

Rio Agent: voice-first autonomous assistant with local and cloud runtimes

SignalWire AI Agents SDK

A voice interface for OpenAI's ChatGPT

Command line tool to transcribe & translate audio from livestreams in real time

Voice MCP for natural conversations with Claude - simple, elegant, wake-word activated

A client for Lollms that allows audio to audio full interaction with Lollms

A voice chatbot based on GPT4All and OpenAI Whisper, running on your PC locally

Telnyx Agent Toolkit — tools for building AI agents with Telnyx APIs

Placeholder for tts_webui_extension.gpt_sovits until migrated from GitHub due to VCS dependencies.

OpenAI compatible TTS API with support for multiple TTS models

Azure integrations for Twilio Agent Connect (TAC) - connectors for Azure AI agent services

A FastAPI server that acts as a TwiML voice agent

Steganography framework for ultrasonic agentic command transmission

Video SDK Agents

VideoSDK Agent Framework plugin for anthropic

VideoSDK Agent Framework plugin for Groq TTS services

VideoSDK Agent Framework plugin for LangChain and LangGraph

VideoSDK Agent Framework plugin for OpenAI services

Production-ready Voice AI infrastructure

A conversational voice companion bot framework for Python. Plug in any LLM and voice tools to create your own assistant.

A voice agent framework for LLM + STT + TTS pipelines

A comprehensive Python library for building production-ready voice agents with multi-provider support. Features real-time streaming TTS/STT, OpenAI, ElevenLabs, and Groq integration, audio processing, and seamless conversational AI capabilities.

Provider-agnostic voice RAG pipeline. Plug in your voice provider, LLM, vector store, and document parsers.

A package to make it easy to interact with LLM's using voice

voice cloning with GPT

A modular Python library for voice interactions with AI systems