Skip to content
Change the repository type filter

All

    Repositories list

    • Resources that make every language unique
      Apache License 2.0
      42700Updated Apr 20, 2026Apr 20, 2026
    • Kotlin
      3000Updated Apr 12, 2026Apr 12, 2026
    • Russian speech technology links
      Apache License 2.0
      2438200Updated Mar 17, 2026Mar 17, 2026
    • vosk-tts

      Public
      Text To Speech Synthesis with Vosk
      Python
      Apache License 2.0
      35256321Updated Mar 14, 2026Mar 14, 2026
    • Automatic Speech Recognition in Unity using Vosk library
      C#
      Apache License 2.0
      2412280Updated Mar 7, 2026Mar 7, 2026
    • An open-source AI Voice Agent that integrates with Asterisk/FreePBX using Audiosocket/RTP technology
      Python
      MIT License
      186200Updated Mar 3, 2026Mar 3, 2026
    • vosk-api

      Public
      Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
      Jupyter Notebook
      Apache License 2.0
      1.7k15k54745Updated Feb 22, 2026Feb 22, 2026
    • Real-time speech recognition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, x86_64 ser…
      C++
      Apache License 2.0
      1.4k1000Updated Jan 29, 2026Jan 29, 2026
    • Website and documentation
      HTML
      222221Updated Jan 7, 2026Jan 7, 2026
    • Offline speech recognition for Android with Vosk library.
      Java
      Apache License 2.0
      2701k724Updated Dec 8, 2025Dec 8, 2025
    • Python
      0000Updated Dec 1, 2025Dec 1, 2025
    • aioice

      Public
      asyncio-based Interactive Connectivity Establishment (RFC 5245)
      Python
      BSD 3-Clause "New" or "Revised" License
      69000Updated Nov 3, 2025Nov 3, 2025
    • aiortc

      Public
      WebRTC and ORTC implementation for Python using asyncio
      Python
      BSD 3-Clause "New" or "Revised" License
      872000Updated Nov 3, 2025Nov 3, 2025
    • vocos

      Public
      Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
      Python
      MIT License
      129000Updated Sep 4, 2025Sep 4, 2025
    • lhotse

      Public
      Tools for handling speech data in machine learning projects.
      Python
      Apache License 2.0
      272000Updated Aug 15, 2025Aug 15, 2025
    • WebSocket, gRPC and WebRTC speech recognition server based on Vosk and Kaldi libraries
      Python
      Apache License 2.0
      3131.3k818Updated Jul 25, 2025Jul 25, 2025
    • clapack

      Public
      CLAPACK clone for our builds
      C
      Other
      13410Updated May 1, 2025May 1, 2025
    • icefall

      Public
      Python
      Apache License 2.0
      409200Updated Apr 11, 2025Apr 11, 2025
    • [ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
      Jupyter Notebook
      MIT License
      195300Updated Dec 12, 2024Dec 12, 2024
    • Dart
      Apache License 2.0
      8175171Updated Oct 26, 2024Oct 26, 2024
    • SDDPM

      Public
      [WACV 2024] Spiking Denoising Diffusion Probabilistic Models
      Python
      12100Updated Oct 9, 2024Oct 9, 2024
    • kaldi

      Public
      An official git mirror of Kaldi project SVN repo
      Shell
      Other
      5.4k5603Updated Aug 23, 2024Aug 23, 2024
    • openfst

      Public
      Openfst mirror with some fixes
      C++
      Other
      181531Updated Aug 23, 2024Aug 23, 2024
    • Faster Whisper ASR transcription with CTranslate2
      Python
      MIT License
      1.8k100Updated Aug 19, 2024Aug 19, 2024
    • A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.
      Apache License 2.0
      241600Updated Aug 11, 2024Aug 11, 2024
    • Speech Recognition in Asterisk with Vosk Server
      C
      GNU General Public License v2.0
      41129203Updated Jun 21, 2024Jun 21, 2024
    • RHVoice

      Public
      a free and open source speech synthesizer for Russian and other languages
      C++
      GNU General Public License v2.0
      263500Updated May 28, 2024May 28, 2024
    • Python
      Apache License 2.0
      0000Updated Apr 24, 2024Apr 24, 2024
    • TTS

      Public
      🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
      Python
      Mozilla Public License 2.0
      6.1k300Updated Apr 8, 2024Apr 8, 2024
    • ffmpeg

      Public
      Mirror of https://git.ffmpeg.org/ffmpeg.git
      C
      Other
      14k000Updated Apr 1, 2024Apr 1, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.