InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

  1. awesome-voice-typing

    Docs & tutorials

    Curated list of open-source speech-to-text and voice typing tools for Linux, macOS, Windows, Android, and iOS. Offline, local, and cloud.

    Indexed GitHub, primaprashant 218 ★MITUpdated today

    git clone https://github.com/primaprashant/awesome-voice-typing.git
  2. Transcribe local audio files and public audio URLs to text, SRT/VTT or word timestamps.

    Stale Official MCP Registry, io.github.Saidwire Updated 15 days ago 2 notes

    saidwire-mcp@0.1.0
  3. automatic speech recognition model by ConwayResearch · transformers

    Stale Hugging Face Hub, ConwayResearch 69 ♥cc-by-4.0Updated 32 days ago

    ConwayResearch/Underdog-Bark-3.0-Clean
  4. automatic speech recognition model by ConwayResearch · transformers

    Stale Hugging Face Hub, ConwayResearch 44 ♥cc-by-4.0Updated 32 days ago

    ConwayResearch/Underdog-Bark-3.0-Pro
  5. DeepSeek-Harness (DSH) 插件:✨ 提示词一键增强(5 模式·模型链·记忆链)+ 💬 语音输入增强(热键·说完自动停·口水词清理·语音纠错)

    Indexed GitHub, Fishsb 130 ★Apache-2.0Updated 3 days ago

    git clone https://github.com/Fishsb/dsh-voice-prompt-enhancer.git
  6. vexa

    MCP servers

    Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.

    Stale GitHub, Vexa-ai 2,934 ★Apache-2.0Updated 16 days ago

    git clone https://github.com/Vexa-ai/vexa.git
  7. Transcribe audio and video files to text with timestamps and SRT or WebVTT subtitles

    Stale Official MCP Registry, io.github.kriton-dev Updated 7 days ago 1 note

  8. flutter_edge_ai

    AI repositories

    On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.

    Indexed GitHub, DenisovAV 665 ★MITUpdated today

    git clone https://github.com/DenisovAV/flutter_edge_ai.git
  9. tiny-audio

    Docs & tutorials

    A speech-to-text system you can train for $25. A frozen speech encoder and a Qwen LLM joined by a small trained projector, with word timestamps, speaker diarization, a batched HTTP server, a live demo, and a free course.

    Stale GitHub, alexkroman 179 ★MITUpdated 15 days ago

    git clone https://github.com/alexkroman/tiny-audio.git
  10. benchmarks

    Agents & frameworks

    Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.

    Stale GitHub, coval-ai 104 ★Custom licence (see repository)Updated 24 days ago

    git clone https://github.com/coval-ai/benchmarks.git
  11. automatic speech recognition model by salesforce-sovereign-intelligence · transformers

    Indexed Hugging Face Hub, salesforce-sovereign-intelligence 59 ♥apache-2.0Updated 5 days ago

    salesforce-sovereign-intelligence/SOV-Transcribe-1
  12. Transcribe audio and video (SRT/VTT subtitles, an hour for $0.05) and text to speech as MP3.

    Indexed Official MCP Registry, io.github.Nutshell2000 Updated today 1 note

  13. eidolon-sc

    AI repositories

    和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身:日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆;支持 Google/GitHub 登录与自带密钥,Docker Compose 一键部署(参考 LAPLACE Eidolon)

    Indexed GitHub, Sallyn0225 437 ★AGPL-3.0Updated today

    git clone https://github.com/Sallyn0225/eidolon-sc.git
  14. automatic speech recognition model by mistralai · vllm

    Stale Hugging Face Hub, mistralai 38 ♥Updated 35 days ago

    mistralai/Voxtral-Mini-4B-Realtime-Arabic
  15. automatic speech recognition model by FermionResearch · mlx

    Stale Hugging Face Hub, FermionResearch 19 ♥cc-by-4.0Updated 19 days ago

    FermionResearch/Phonon-2.5-English
  16. orbit

    AI repositories

    Self-hosted AI gateway for private RAG, natural-language data access, and tool-calling agents.

    Indexed GitHub, schmitech 364 ★Apache-2.0Updated today

    git clone https://github.com/schmitech/orbit.git
  17. Phonon-2.5

    Models

    automatic speech recognition model by FermionResearch · mlx

    Stale Hugging Face Hub, FermionResearch 42 ♥cc-by-4.0Updated 19 days ago

    FermionResearch/Phonon-2.5
  18. vllm-mlx

    AI repositories

    High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

    Stale GitHub, waybarrios 1,646 ★Apache-2.0Updated 11 days ago

    git clone https://github.com/waybarrios/vllm-mlx.git
  19. text to speech model by inclusionAI · transformers

    Stale Hugging Face Hub, inclusionAI 65 ♥mitUpdated 25 days ago

    inclusionAI/Ming-3.0-audio-flash
  20. blurt

    Skills

    The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your other agents. Free, open source, Mac. 口喷鸡:Agent 时代的输入法。

    Indexed GitHub, AGIHunt 389 ★MITUpdated today

    git clone https://github.com/AGIHunt/blurt.git
  21. text to speech model by inclusionAI · transformers

    Stale Hugging Face Hub, inclusionAI 50 ♥mitUpdated 26 days ago

    inclusionAI/Ming-3.0-audio-tiny
  22. automatic speech recognition model by AtomicChat · gguf

    Stale Hugging Face Hub, AtomicChat 37 ♥otherUpdated 19 days ago

    AtomicChat/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-GGUF
  23. AI-Interview

    Agents & frameworks

    开源的 AI 模拟面试系统:真人数字人面试官开口提问、按你的回答追问,报告逐题打分;另含 Docker 判题笔试与 AI 简历优化。Java 21 + Spring AI Alibaba + Vue 3。

    Stale GitHub, xgwangdl 234 ★Apache-2.0Updated 28 days ago

    git clone https://github.com/xgwangdl/AI-Interview.git
  24. Lampline

    AI repositories

    Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.

    Stale GitHub, C4rohan 530 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/C4rohan/Lampline.git

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.