Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
streamcore-server
Agents & frameworksOpen-source realtime voice agent server in Go with WebRTC (WHIP), barge-in, streaming STT/LLM/TTS pipelines, plugin system, multi-language SDKs, SIP telephony, ESP32 support & fully local mode.
git clone https://github.com/streamcoreai/streamcore-server.git -
Liquid-Codec
Modelsfeature extraction model by LiquidAI · transformers
LiquidAI/Liquid-Codec -
MusicCaps
Datasets & benchmarksHugging Face dataset by google
google/MusicCaps -
Subtly
MCP serversTranscribe audio and video, and translate subtitles into 50+ languages.
-
voiceblender
Agents & frameworksA programmable Voice AI platform: SIP and WebRTC call control, multi-party mixing, recording, TTS/STT, and pluggable AI agents (ElevenLabs, VAPI, Pipecat, Deepgram) — all driven through a REST API, webhooks, and a WebSocket event stream
git clone https://github.com/VoiceBlender/voiceblender.git -
Zernote
MCP serversUser research workspace to transcribe interviews and turn conversations into insights.
-
Awesome-Prompt-Engineering
PromptsThis repository contains a hand-curated resources for Prompt Engineering with a focus on Generative Pre-trained Transformer (GPT), ChatGPT, PaLM etc
git clone https://github.com/promptslab/Awesome-Prompt-Engineering.git -
OpenCreator
SkillsFormerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.
git clone https://github.com/krillinai/OpenCreator.git -
cactus
Modelstext generation model by Cactus-Compute · cactus-compute
Cactus-Compute/cactus -
PodcastsToText
MCP serversTranscribe podcasts, YouTube and audio, then make show notes, chapters and translations.
-
Blumify
MCP serversTranscribe YouTube videos and podcasts, then summarize, ask, translate and follow creators.
-
Dadan
MCP serversScreen recording & video platform: search, share, transcribe, translate videos & AI meeting notes
-
ReelScribe
MCP serversTranscribe social videos, selected comments, URL batches and Instagram channels.
-
Neural Analog
MCP serversImport, restore, master, split, transcribe, and download audio with Neural Analog.
-
Parlova
MCP serversTranscribe local audio/video and YouTube into timestamped, speaker-labelled text. 90+ languages.
parlova@1.0.1 -
IBM Text to Speech
Public APIsConvert text to speech
-
voice-reader
Modelsaudio classification model by pipecat-ai · onnx
pipecat-ai/voice-reader -
chubbyskills
Skills把中文全渠道内容(抖音 / B站 / 小红书 / 公众号 / X / 播客)采集进个人知识库的 14 个 AI Skill:图文存图、视频转文字稿、字幕优先免 GPU、RSS/YouTube 订阅调度与每日情报简报,附带知识库 MCP server。| Ingest Chinese content into your personal knowledge base — image/video routing, subtitle-first transcription, feed subscriptions with daily digests, and a KB MCP server.
git clone https://github.com/chubbyguan/chubbyskills.git -
pronounce
Skills🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP + Agent Skill.
git clone https://github.com/anzy-renlab-ai/pronounce.git -
anymd
MCP serversAny file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP server and CLI that runs on your machine. No API key.
git clone https://github.com/SylphxAI/anymd.git -
Uttera
MCP serversAudio for your agent: transcribe, speak, translate, summarise, plus sound effects and music.
-
Shorty
MCP serversSummarize and transcribe videos, audio, documents and web pages; subtitles; search your library.
-
ihateaudio
MCP servers49 audio tools: trim, convert, normalize, remove vocals, split stems, transcribe, and more.
-
Lemma Telepath
MCP serversSearch, read and reply to your Telegram Business chats, transcribed voice included.
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.