izwi-ai/izwi

Voice AI runtime. Local first transcription, speaker diarization, TTS, and voice cloning with an OpenAI compatible API.

GitHub repository with 336 stars and 34 forks.

Language: Rust

Topics: asr, local-first, openai-compatible-api, self-hosted-ai, speaker-diarization, speech-to-text, text-to-speech, tts, voice-cloning, audio-inference

Open provider repository

Latest metric snapshot

2026-06-05: 336 stars and 34 forks.

Similar repositories

  1. 1. drakulavich/kesha-voice-kit

    Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.

    GitHub repository with 48 stars and 7 forks.

    Trending score: 0.77; stars gained: +5; forks gained: +0.

    Language: Rust

    Topics: apple-silicon, asr, bun, coreml, openclaw, speech-to-text

Trending in Rust

  1. 1. BigPizzaV3/CodexPlusPlus

    An enhanced tool for CodexApp, striving to make Codex better to use and more comfortable 一个CodexApp的增强工具,努力让Codex变得更好用更舒服

    GitHub repository with 14,052 stars and 871 forks.

    Trending score: 5.16; stars gained: +916; forks gained: +44.

    Language: Rust

  2. 2. rtk-ai/rtk

    CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

    GitHub repository with 59,182 stars and 3,643 forks.

    Trending score: 4.96; stars gained: +654; forks gained: +44.

    Language: Rust

    Topics: agentic-coding, ai-coding, anthropic, claude-code, cli, command-line-tool

  3. 3. openai/codex

    Lightweight coding agent that runs in your terminal

    GitHub repository with 88,934 stars and 13,072 forks.

    Trending score: 4.58; stars gained: +326; forks gained: +48.

    Language: Rust

  4. 4. tinyhumansai/openhuman

    Your Personal AI super intelligence. Private, Simple and extremely powerful.

    GitHub repository with 30,877 stars and 2,982 forks.

    Trending score: 4.37; stars gained: +332; forks gained: +50.

    Language: Rust

  5. 5. fallow-rs/fallow

    Codebase intelligence for TypeScript and JavaScript. Free static layer: unused code, duplication, circular deps, complexity hotspots, architecture boundaries. Optional paid runtime layer: hot-path review and cold-path deletion evidence from real production traffic. Rust-native, sub-second, zero-config framework support.

    GitHub repository with 3,118 stars and 96 forks.

    Trending score: 4.05; stars gained: +346; forks gained: +16.

    Language: Rust

    Topics: cli, code-duplication, code-quality, codebase-intelligence, copy-paste-detection, dead-code

  6. 6. openlake-project/openlake

    OpenLake is a high performance object store for LLM Inference and GPU Training. Feed your GPUs at blazing fast speeds.

    GitHub repository with 1,108 stars and 176 forks.

    Trending score: 4.00; stars gained: +244; forks gained: +120.

    Language: Rust

    Topics: blackwell, gpt, gpu, high-performance, llm, llm-training

Trending topic: asr

  1. 1. Open-Less/openless

    Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话,松开即得润色后的文字)

    GitHub repository with 2,150 stars and 169 forks.

    Trending score: 2.75; stars gained: +25; forks gained: +1.

    Language: HTML

    Topics: ai-prompt, asr, dictation, linux, llm, macos

  2. 2. xzf-thu/Mega-ASR

    First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come back to MEGA-ASR, after the rest fail in the wild. ⭐**

    GitHub repository with 957 stars and 61 forks.

    Trending score: 2.72; stars gained: +33; forks gained: -1.

    Language: Python

    Topics: asr, robust

  3. 3. modelscope/FunASR

    Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

    GitHub repository with 16,750 stars and 1,720 forks.

    Trending score: 1.93; stars gained: +56; forks gained: +2.

    Language: Python

    Topics: pytorch, speech-recognition, paraformer, punctuation, speaker-diarization, voice-activity-detection

  4. 4. Soul-AILab/SoulX-Transcriber

    An end-to-end framework for multi-speaker transcription that jointly models who spoke, when, and what.

    GitHub repository with 183 stars and 7 forks.

    Trending score: 1.58; stars gained: +40; forks gained: +5.

    Language: Python

    Topics: asr, llm, sd, sdr, speech-recognition

  5. 5. k2-fsa/sherpa-onnx

    Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

    GitHub repository with 12,737 stars and 1,453 forks.

    Trending score: 1.41; stars gained: +29; forks gained: +1.

    Language: C++

    Topics: asr, onnx, windows, linux, macos, cpp

  6. 6. BillLucky/echocut

    Turn raw footage into brand-ready, platform-optimized video with one command. Local-first: FFmpeg + WhisperX/MLX + Ollama.

    GitHub repository with 51 stars and 12 forks.

    Trending score: 0.89; stars gained: +7; forks gained: +1.

    Language: JavaScript

    Topics: asr, captions, cli, ffmpeg, llm, local-first