#speech-to-speech Repositories
Discover 16 active open source GitHub repositories tagged with #speech-to-speech, accumulating 35,295 total stars (averaging 2,205 stars per project). Leading this topic is dograh-hq/dograh with 6,240 stars.
17 repositories total
Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On-prem, BYOK across Speech-to-Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
A simple, high-quality voice conversion tool focused on ease of use and performance.
open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.
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.
Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets & Edge Functions for AI Toys, Desk Companions and Devices
AI speech toolkit for Apple Silicon โ ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
Voice AI Girlfriend (Voice AI girlfriend for DeepSeek Harness): Whisper voice input + Qwen3-TTS voice cloning + sentence-level streaming playback + animated avatar window. Dual interrupt/queue modes: speaking immediately interrupts.
Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.
A lightning-fast, cross-platform mobile AI Assistant App built with React Native.
Self-hosted, API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans can take over without dropping it. Runs on FreeSWITCH with your SIP trunk and a real-time model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway).
World's first open-source real-time endโtoโend spoken dialogue model with personalized voice cloning.
High-quality and streaming Speech-to-Speech interactive agent in a single file. Streaming full-duplex voice interaction prototype intelligent agent implemented with only one file!
Open full-duplex voice models that hear your tone and speak with one. One GPU with vLLM-Omni, or fully offline on a Mac with MLX. Zero-shot voice cloning, OpenAI Realtime / GPT-Live compatible, free hosted API trial. Apache-2.0.
Frequently Asked Questions
What is the most popular #speech-to-speech repository on GitHub?
The top ranked open source #speech-to-speech project on GitHub is dograh-hq/dograh with 6,240 stars. Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On-prem, BYOK across Speech-to-Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.
Which programming languages are most used in #speech-to-speech repositories?
Among the top ranked #speech-to-speech projects on GitHub, the most common programming languages are Python, TypeScript, Swift, C++.
How is the #speech-to-speech repository ranking calculated?
We track 16 active open source repositories tagged with #speech-to-speech (500+ stars), totaling 35,295 stars with an average of 2,205 stars per repository. Rankings update daily from the GitHub API.