Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
voice-ai
Agents & frameworksRapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.
git clone https://github.com/rapidaai/voice-ai.git -
LTX-2
AI repositoriesOfficial Python inference and LoRA trainer package for the LTX-2 audio–video generative model.
git clone https://github.com/Lightricks/LTX-2.git -
BikeWise API v2
Public APIsThis is an API for accessing information about bicycling related incidents. You can find the source code on GitHub .
-
Creator SKILL v2 — Influencer Discovery
MCP serversSKILL-02 (not SKILL-01): AI influencer search on TikTok, Instagram & YouTube. sk_live_ token.
creator-skill-v2@0.2.1 -
FLOP Independent MCP V2
MCP serversBounded readonly SHA256 verification with the official MCP SDK. No code execution or model calls.
-
Spinitron v2 API
Public APIsNotes Tutorial demo using this API is at https://spinitron.com/v2-api-demo/ (https://spinitron.com/v2-api-demo/). For web integration using iframes and/or JavaScript instead of an API, see https://spinitron.github.io/v2-web-integration/ (https://spinitron.github.io/v2-web-integration/). Your API key is found in the Spinitron web app. Log in to Spinitron and go to Automation & API in the Admin…
-
japanese-anime-speech
Datasets & benchmarksHugging Face dataset by joujiboi
joujiboi/japanese-anime-speech -
text to video model by Veda-Sparse · minimax-h3
Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview -
muscriptor-medium
Modelsmodel by MuScriptor · muscriptor
MuScriptor/muscriptor-medium -
Cosmos3-Nano
Modelsmodel by nvidia · cosmos
nvidia/Cosmos3-Nano -
screenpipe
AI repositoriesYC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
git clone https://github.com/screenpipe/screenpipe.git -
librispeech_asr
Datasets & benchmarksHugging Face dataset by openslr
openslr/librispeech_asr -
text to speech model by Qwen · qwen-tts
Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign -
parakeet-tdt-0.6b-v3
Modelsautomatic speech recognition model by nvidia · transformers
nvidia/parakeet-tdt-0.6b-v3 -
clef-omni
Modelsimage text to text model by Cloudflare · transformers
Cloudflare/clef-omni -
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 -
aisearch-openai-rag-audio
AI repositoriesA simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.
git clone https://github.com/Azure-Samples/aisearch-openai-rag-audio.git -
ai-creator-academy
Agents & frameworksFree, open-source curriculum for making money with generative AI image, video, and audio — for creators and agencies.
git clone https://github.com/Anil-matcha/ai-creator-academy.git -
cohere-transcribe-03-2026
Modelsautomatic speech recognition model by CohereLabs · transformers
CohereLabs/cohere-transcribe-03-2026 -
ffmpeg-skill
MCP serversLocal FFmpeg video and audio tools over stdio. Footage stays on this machine.
ffmpeg-skill@3.10.1 -
text to video model by smhfacct
smhfacct/Minimax-H3-fl2va-ref2va-hybrid-models -
abogen
AI repositoriesGenerate audiobooks from EPUBs, PDFs and text with synchronized captions.
git clone https://github.com/denizsafak/abogen.git -
Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instructions must be supplied through a JSON schema...
inference-net/schematron-v2-small -
gemma-3n-E4B-it
Modelsimage text to text model by google · transformers
google/gemma-3n-E4B-it
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.