speech-to-speech repositories
Trending repositories tagged speech-to-speech, ranked by trending score. Updated daily.
-
1
adventists-ai/sophon-realtime
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.
GitHub · Python · 520 stars · 45 forks · +36 stars in 24 hours · Trending score 3.19
-
2
0xShug0/audio.cpp
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.
GitHub · C++ · 4,410 stars · 549 forks · +28 stars in 24 hours · Trending score 3.12
-
3
rasonyang/ai-native-callcenter
Self-hosted API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans take over without dropping it. Runs on FreeSWITCH with your SIP trunk and realtime model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway).
GitHub · Go · 727 stars · 146 forks · +32 stars in 24 hours · Trending score 3.02
-
4
beiyege-01/dsh-voice-ai-girlfriend
语音 AI 女友(Voice AI girlfriend for DeepSeek Harness):Whisper 语音输入 + Qwen3-TTS 声音克隆 + 句子级流式朗读 + 数字人动画窗。插话/排队双模式,说话即打断。
GitHub · TypeScript · 1,104 stars · 315 forks · +55 stars in 24 hours · Trending score 3.02
-
5
bielcarpi/hermes-live-voice
Self-hosted realtime voice gateway for Hermes Agent. Keep talking while Hermes runs background tasks through local, Gemini Live, and OpenAI Realtime adapters.
GitHub · TypeScript · 90 stars · 15 forks · +21 stars in 24 hours · Trending score 2.13
-
6
TheSmokeDev/hermes-talk
Hermes Talk: realtime duplex voice for Hermes Agent. Rides your ChatGPT or X Premium subscription, no API key needed. OpenAI, Grok, Gemini. Terminal, Discord, dashboard.
GitHub · Python · 205 stars · 36 forks · +3 stars in 24 hours · Trending score 2.10
-
7
akdeb/ElatoAI
Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets & Edge Functions for AI Toys, Desk Companions and Devices
GitHub · TypeScript · 2,124 stars · 264 forks · +1 stars in 24 hours · Trending score 1.48
-
8
IAHispano/Applio
A simple, high-quality voice conversion tool focused on ease of use and performance.
GitHub · Python · 4,040 stars · 634 forks · 0 stars in 24 hours · Trending score 1.36
-
9
rasonyang/cascade-realtime-gateway
Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind it. Keep clients unchanged while swapping speech and LLM providers at runtime
GitHub · Go · 65 stars · 8 forks · +5 stars in 24 hours · Trending score 1.33
-
10
pegainfer-project/kern-omni
OpenAI-compatible speech serving in Rust: streaming TTS and full-duplex voice over GPT-Live. 128 concurrent PersonaPlex sessions on one GPU.
GitHub · Rust · 54 stars · 5 forks · +4 stars in 24 hours · Trending score 1.30
-
11
dograh-hq/dograh
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.
GitHub · Python · 6,242 stars · 1,617 forks · 0 stars in 24 hours · Trending score 1.21
-
12
kccarlos/herdr-sheepdog
Manage your Herdr agents by voice — hands-free, from anywhere. A voice-first agent harness for Claude Code, Codex and other coding agents, with an iPhone app.
GitHub · Go · 23 stars · 3 forks · +2 stars in 24 hours · Trending score 1.14
-
13
cgoinglove/thursday-agent
Talk, and a team of bots does the work in a real browser, a shell and your files while she keeps talking. Open source, runs on your machine, on your ChatGPT plan or an OpenAI key. npx thursday-agent
GitHub · TypeScript · 58 stars · 13 forks · 0 stars in 24 hours · Trending score 0.95
-
14
xcc-zach/xtalk
X-Talk is an open-source full-duplex cascaded spoken dialogue system framework enabling low-latency, interruptible, and human-like speech interaction with a lightweight, pure-Python, production-ready architecture.
GitHub · Python · 250 stars · 33 forks · +3 stars in 24 hours · Trending score 0.90
-
15
JMS1717/ming-voice
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
GitHub · Python · 451 stars · 26 forks · +1 stars in 24 hours · Trending score 0.90
-
16
microsoft/voice-agent
voice agent in foundry agent service
GitHub · JavaScript · 11 stars · 14 forks · +1 stars in 24 hours · Trending score 0.86
-
17
insta-fusion/bettercallgpt
Put Claude Code on a voice call. Talk while it codes; GPT Realtime talks back.
GitHub · Python · 10 stars · 3 forks · +2 stars in 24 hours · Trending score 0.83
-
18
runboubou/boubou
Run voice AI locally with open-source models. Bring it to any device with one command.
GitHub · Rust · 100 stars · 16 forks · 0 stars in 24 hours · Trending score 0.81
-
19
speakrail/speakrail
Speakrail - a low-latency fully-local voice assistant
GitHub · Python · 216 stars · 28 forks · +1 stars in 24 hours · Trending score 0.75
-
20
aws-samples/sample-mobile-ai-assistant
A lightning-fast, cross-platform mobile AI Assistant App built with React Native.
GitHub · TypeScript · 871 stars · 139 forks · +2 stars in 24 hours · Trending score 0.74
-
21
soniqo/speech-swift
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
GitHub · Swift · 1,284 stars · 193 forks · 0 stars in 24 hours · Trending score 0.65
-
22
coval-ai/benchmarks
Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.
GitHub · Python · 106 stars · 16 forks · +1 stars in 24 hours · Trending score 0.64
-
23
quangdang46/livekit_agent_simulator
Black-box LiveKit voice agent testing: real WebRTC/SIP calls with an AI caller. Catch barge-in, noise, quiet-mic, and latency failures that text pytest misses. Forensic reports + MCP + lks CLI — no agent code changes.
GitHub · Python · 7 stars · 2 forks · +1 stars in 24 hours · Trending score 0.46
-
24
927tanmay/react-ai-voice-avatar
Voice mode for your React app, on your own LLM and speech vendors. Turn-taking, barge-in and streamed speech in one hook, with an optional lip-synced 3D avatar. 📦 npm: react-ai-voice-avatar
GitHub · TypeScript · 22 stars · 5 forks · +1 stars in 24 hours · Trending score 0.45