Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
speaker-diarization-3.1
Modelsautomatic speech recognition model by pyannote · pyannote-audio
pyannote/speaker-diarization-3.1 -
automatic speech recognition model by pyannote · pyannote-audio
pyannote/speaker-diarization-community-1 -
speaker-diarization
Modelsautomatic speech recognition model by pyannote · pyannote-audio
pyannote/speaker-diarization -
FunASR
MCP serversOpen-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
git clone https://github.com/modelscope/FunASR.git -
Nemotron-3-Diarization
Modelsvoice activity detection model by nvidia · nemo
nvidia/Nemotron-3-Diarization -
segmentation-3.0
Modelsvoice activity detection model by pyannote · pyannote-audio
pyannote/segmentation-3.0 -
automatic speech recognition model by nvidia · nemo
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B -
audio.cpp-gguf
Modelstext to speech model by audio-cpp · audio.cpp
audio-cpp/audio.cpp-gguf -
Audio & video to text, Russian-first: diarization, timestamps, summary, action items, subtitles.
-
tiny-audio
Docs & tutorialsA 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.
git clone https://github.com/alexkroman/tiny-audio.git -
automatic speech recognition model by AtomicChat · gguf
AtomicChat/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-GGUF -
automatic speech recognition model by nvidia · nemo
nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-NVFP4 -
Parrot
AI repositoriesMeeting recorder for your Mac with a live AI assistant. On-device transcription, answers from your own docs mid-call. Local-first and open source.
git clone https://github.com/turantekin/Parrot.git -
yaya-skills
SkillsAgent Skills 把 X Space 变成中文干货笔记:下载 → 带说话人转写 → LLM 蒸馏 → 分享图 / Turn X Spaces into distilled Chinese notes with speaker labels & share cards.
git clone https://github.com/eatmoreduck/yaya-skills.git -
humla
AI repositoriesOpen-source AI meeting notes for Mac. Records mic + system audio with no bot, transcribes on-device or via OpenAI / Deepgram / Groq, identifies speakers offline, and writes summaries that fuse your notes with the transcript. Ask your notes and get cited answers. Tauri 2 + Rust + Swift.
git clone https://github.com/michaelwilhelmsen/humla.git -
particle-pro
MCP serversPodcast intelligence for agents: transcripts, clips, speaker diarization, mention tracking.
-
Nojoin
MCP serversSelf-hosted meeting notes with no bot in the call. Records Meet, Teams and Zoom from the browser, transcribes on your own hardware, and lets Claude or ChatGPT read and edit your library over MCP.
git clone https://github.com/Valtora/Nojoin.git -
ffvoice
MCP serversOffline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud
ffvoice@0.8.3 -
meetily
AI repositoriesPrivacy-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
git clone https://github.com/Zackriya-Solutions/meetily.git -
Transcreva
MCP serversBrazilian Portuguese audio and video transcription with speaker diarization and SRT/VTT/DOCX export.
-
Transcreva
MCP serversBrazilian Portuguese audio and video transcription with speaker diarization and SRT/VTT/DOCX export.
-
fortemi
MCP serversSelf-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
git clone https://github.com/Fortemi/fortemi.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.