InnerVault

Library

85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. Whisper

    Models

    OpenAI's open speech-to-text model.

    Hand-checked InnerVault (hand-checked), OpenAI MIT

    pip install -U openai-whisper
  2. fastrtc

    AI repositories

    The python library for real-time communication

    Stale GitHub, gradio-app 4,631 ★MITUpdated 10 months ago

    git clone https://github.com/gradio-app/fastrtc.git
  3. awesome-whisper

    Docs & tutorials

    🔊 Awesome list for Whisper — an open-source AI-powered speech recognition system developed by OpenAI

    Stale GitHub, sindresorhus 2,417 ★CC0-1.0Updated 2 months ago

    git clone https://github.com/sindresorhus/awesome-whisper.git
  4. VibeVoice-ASR

    Models

    automatic speech recognition model by microsoft · transformers

    Indexed Hugging Face Hub, microsoft 1,330 ♥mitUpdated 9 months ago

    microsoft/VibeVoice-ASR
  5. WhisperJAV

    AI repositories

    ASR/STT subtitle generator. Uses Qwen3-ASR, local LLM, Whisper, TEN-VAD. Noise-robust for JAV

    Stale GitHub, meizhong986 2,394 ★MITUpdated 17 days ago

    git clone https://github.com/meizhong986/WhisperJAV.git
  6. Phonon-2

    Models

    automatic speech recognition model by FermionResearch · mlx

    Stale Hugging Face Hub, FermionResearch 370 ♥cc-by-4.0Updated 24 days ago

    FermionResearch/Phonon-2
  7. VivaDicta

    AI repositories

    iOS & watchOS speech-to-text app with AI voice keyboard, on-device RAG, and chat with your notes - powered by Apple Foundation Models, WhisperKit, NVIDIA Parakeet, and 20+ AI providers

    Indexed GitHub, n0an 144 ★MITUpdated 2 days ago

    git clone https://github.com/n0an/VivaDicta.git
  8. automatic speech recognition model by nvidia · nemo

    Indexed Hugging Face Hub, nvidia 3,336 ♥otherUpdated 18 days ago

    nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
  9. 🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API,支持 AI agent 通过 MCP 调用与离线语音转文字,Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.

    Stale GitHub, Evil0ctal 21.1k ★Apache-2.0Updated 14 days ago

    git clone https://github.com/Evil0ctal/Douyin_TikTok_Download_API.git
  10. whistle

    Models

    automatic speech recognition model by Cactus-Compute · cactus-compute

    Stale Hugging Face Hub, Cactus-Compute 569 ♥apache-2.0Updated 11 days ago

    Cactus-Compute/whistle
  11. screenpipe

    AI repositories

    YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

    Indexed GitHub, screenpipe 22.4k ★Custom licence (see repository)Updated 2 days ago

    git clone https://github.com/screenpipe/screenpipe.git
  12. FunASR

    MCP servers

    Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.

    Indexed GitHub, modelscope 21.0k ★MITUpdated yesterday

    git clone https://github.com/modelscope/FunASR.git
  13. s1-mini

    Models

    text generation model by superwhisper · transformers

    Stale Hugging Face Hub, superwhisper 378 ♥otherUpdated 2 months ago

    superwhisper/s1-mini
  14. FunClip

    AI repositories

    FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.

    Stale GitHub, modelscope 6,480 ★MITUpdated 15 days ago

    git clone https://github.com/modelscope/FunClip.git
  15. automatic speech recognition model by facebook · fairseq2

    Stale Hugging Face Hub, facebook 513 ♥cc-by-nc-4.0Updated 2 years ago

    facebook/seamless-m4t-large
  16. ODS

    Agents & frameworks

    ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn your PC, Mac, or Linux box into a private AI server.

    Indexed GitHub, Osmantic 7,835 ★Apache-2.0Updated today

    git clone https://github.com/Osmantic/ODS.git
  17. openless

    Prompts

    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)

    Indexed GitHub, Open-Less 4,109 ★AGPL-3.0Updated today

    git clone https://github.com/Open-Less/openless.git
  18. Converts audio to text by applying powerful neural network models.

    Indexed APIs.guru OpenAPI Directory, Google Updated 3 years ago

  19. Pay-per-minute speech-to-text: audio URL to text, SRT or VTT. Paid via x402 or credits.

    Stale Official MCP Registry, co.youraitools Updated 22 days ago 1 note

  20. meetily

    AI repositories

    Privacy-first AI meeting note taker for Windows and macOS. Free, open source (MIT). On-device Whisper/Parakeet transcription and speaker diarization, no meeting bot. Open-source alternative to Granola, Otter and Fireflies. https://meetily.ai

    Indexed GitHub, Zackriya-Solutions 32.7k ★MITUpdated 3 days ago

    git clone https://github.com/Zackriya-Solutions/meetily.git
  21. automatic speech recognition model by ConwayResearch · transformers

    Stale Hugging Face Hub, ConwayResearch 86 ♥cc-by-4.0Updated 32 days ago

    ConwayResearch/Underdog-Bark-3.0
  22. BiBi-Keyboard

    AI repositories

    说点啥(BiBi Keyboard):一个基于 Kotlin 的 Android 平台的 LLM 与 ASR 语音输入法键盘应用 An LLM ASR voice input method keyboard application for the Android platform based on Kotlin

    Indexed GitHub, BryceWG 875 ★Apache-2.0Updated 2 days ago

    git clone https://github.com/BryceWG/BiBi-Keyboard.git
  23. Whisper speech to text for podcast, audio and video URLs, 90+ languages, timestamped output.

    Stale Official MCP Registry, io.github.saulius876-lgtm Updated 45 days ago 1 note

  24. Speech denoise, transcripts (SRT/VTT), embeddings, reranking, entities and translation.

    Stale Official MCP Registry, dev.tanod Updated 7 days ago 1 note

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.