Library
85,762 resources from 11 public sources. 53 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 -
Paradee-8M-v1.2
Modelstext to speech model by sahilmahendrakar · onnx
sahilmahendrakar/Paradee-8M-v1.2 -
automatic speech recognition model by pyannote · pyannote-audio
pyannote/speaker-diarization-community-1 -
mithi-v1-flash
Modelstext to speech model by Oomni
Oomni/mithi-v1-flash -
voicemode
MCP serversNatural voice conversations for AI assistants - STT/TTS via MCP
voice-mode@9.0.2 -
TTS-WebUI
AI repositoriesA single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark!
git clone https://github.com/rsxdalv/TTS-WebUI.git -
hurston-1
Modelstext to speech model by destined
destined/hurston-1 -
Speech AI - Pronunciation, STT & TTS
MCP serversPronunciation scoring, speech-to-text, and text-to-speech for language learning
-
speaker-diarization
Modelsautomatic speech recognition model by pyannote · pyannote-audio
pyannote/speaker-diarization -
segmentation-3.0
Modelsvoice activity detection model by pyannote · pyannote-audio
pyannote/segmentation-3.0 -
OmniVoice
Modelstext to speech model by k2-fsa · omnivoice
k2-fsa/OmniVoice -
chatterbox-turbo
Modelstext to speech model by ResembleAI
ResembleAI/chatterbox-turbo -
ED-Outrider
MCP serversExploration companion for Elite Dangerous: undiscovered systems nearby, body values and likely exobiology before you land, an in-game overlay, unsold data, the Neutron Highway, EDDN/EDSM uploads, a natural voice and a tablet layout. Runs on your own PC from your journals; Linux first, Windows and Docker too.
git clone https://github.com/weslocke/ED-Outrider.git -
segmentation
Modelsvoice activity detection model by pyannote · pyannote-audio
pyannote/segmentation -
VoxCPM-0.5B
Modelstext to speech model by openbmb · voxcpm
openbmb/VoxCPM-0.5B -
OpenVoiceV2
Modelstext to speech model by myshell-ai
myshell-ai/OpenVoiceV2 -
OpenVoice
Modelstext to speech model by myshell-ai
myshell-ai/OpenVoice -
VoxCPM1.5
Modelstext to speech model by openbmb · voxcpm
openbmb/VoxCPM1.5 -
maya1
Modelstext to speech model by maya-research · transformers
maya-research/maya1 -
Vision-Agents
Agents & frameworksOpen Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
git clone https://github.com/GetStream/Vision-Agents.git -
unsloth
AI repositoriesLocal UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
git clone https://github.com/unslothai/unsloth.git -
react-speech-highlight-demo
PromptsReact / Vanilla JS Text to Speech with highlighting the words and sentences that are being spoken using audio files, text to speech API, and web speech synthesis API
git clone https://github.com/albirrkarim/react-speech-highlight-demo.git -
Dot
AI repositoriesText-To-Speech, RAG, and LLMs. All local!
git clone https://github.com/alexpinel/Dot.git -
awesome-voice-typing
Docs & tutorialsCurated list of open-source speech-to-text and voice typing tools for Linux, macOS, Windows, Android, and iOS. Offline, local, and cloud.
git clone https://github.com/primaprashant/awesome-voice-typing.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.