Git Stars Git Stars

#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.

16
Total Repositories
35,295
Total Stars
2,205
Avg Stars/Repo
1
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.

dograh-hq
โญ 6,240 Python ๐Ÿ‘ค dograh-hq Organization ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2025-09-09
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.

0xShug0
โญ 4,385 C++ ๐Ÿ‘ค 0xShug0 User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-06-23
3
IAHispano/Applio

A simple, high-quality voice conversion tool focused on ease of use and performance.

IAHispano
โญ 4,048 Python ๐Ÿ‘ค IAHispano Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2023-08-07
4
gpt-omni/mini-omni

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.

gpt-omni
โญ 3,504 Python ๐Ÿ‘ค gpt-omni Organization ๐Ÿ• Updated 2024-11-05 ๐Ÿ“… Created 2024-08-27
5
ictnlp/LLaMA-Omni

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.

ictnlp
โญ 3,142 Python ๐Ÿ‘ค ictnlp Organization ๐Ÿ• Updated 2025-05-19 ๐Ÿ“… Created 2024-09-10
6
zai-org/GLM-4-Voice

GLM-4-Voice | End-to-End Chinese-English Voice Dialogue Model

zai-org
โญ 3,108 Python ๐Ÿ‘ค zai-org Organization ๐Ÿ• Updated 2024-12-05 ๐Ÿ“… Created 2024-10-24
7
akdeb/ElatoAI

Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets & Edge Functions for AI Toys, Desk Companions and Devices

akdeb
โญ 2,122 TypeScript ๐Ÿ‘ค akdeb User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2025-04-08
8
gpt-omni/mini-omni2

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities.

gpt-omni
โญ 1,896 Python ๐Ÿ‘ค gpt-omni Organization ๐Ÿ• Updated 2025-01-16 ๐Ÿ“… Created 2024-10-14
9
soniqo/speech-swift

AI speech toolkit for Apple Silicon โ€” ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML

soniqo
โญ 1,284 Swift ๐Ÿ‘ค soniqo Organization ๐Ÿ• Updated 2026-11-18 ๐Ÿ“… Created 2026-02-04
10
beiyege-01/dsh-voice-ai-girlfriend

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.

beiyege-01
โญ 1,104 TypeScript ๐Ÿ‘ค beiyege-01 User ๐Ÿ• Updated 2026-11-02 ๐Ÿ“… Created 2026-08-15
11
QwenAudio/Fun-Audio-Chat

Fun-Audio-Chat is a Large Audio Language Model built for natural, low-latency voice interactions.

QwenAudio
โญ 1,014 Python ๐Ÿ‘ค QwenAudio Organization ๐Ÿ• Updated 2026-09-24 ๐Ÿ“… Created 2025-12-23
12
aws-samples/sample-mobile-ai-assistant

A lightning-fast, cross-platform mobile AI Assistant App built with React Native.

aws-samples
โญ 871 TypeScript ๐Ÿ‘ค aws-samples Organization ๐Ÿ• Updated 2026-11-12 ๐Ÿ“… Created 2024-11-06
13
Neywa-Labs/mlx-audio-swift

A modular Swift SDK for audio processing with MLX on Apple Silicon

Neywa-Labs
โญ 822 Swift ๐Ÿ‘ค Neywa-Labs Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-12-03
14
rasonyang/ai-native-callcenter

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).

rasonyang
โญ 707 Go ๐Ÿ‘ค rasonyang User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-08-11
15
FlashLabs-AI-Corp/FlashLabs-Chroma

World's first open-source real-time endโ€‘toโ€‘end spoken dialogue model with personalized voice cloning.

FlashLabs-AI-Corp
โญ 552 Jupyter Notebook ๐Ÿ‘ค FlashLabs-AI-Corp Organization ๐Ÿ• Updated 2026-09-04 ๐Ÿ“… Created 2025-11-13
16
opendilab/CleanS2S

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!

opendilab
โญ 543 Python ๐Ÿ‘ค opendilab Organization ๐Ÿ• Updated 2026-04-07 ๐Ÿ“… Created 2024-09-26
17
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.

adventists-ai
โญ 510 Python ๐Ÿ‘ค adventists-ai Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2026-11-04

Frequently Asked Questions

1

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.

2

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++.

3

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.