InnerVault

Library

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

Results

  1. model by FastVideo · diffusers

    Stale Hugging Face Hub, FastVideo 54 ♥otherUpdated 27 days ago

    FastVideo/FastVideo-FastH3-Omni-8-Step-V1
  2. image text to text model by tencent · transformers

    Stale Hugging Face Hub, tencent 114 ♥otherUpdated 37 days ago

    tencent/Youtu-Parsing-Omni
  3. text to video model by drbaph · minimax-h3

    Stale Hugging Face Hub, drbaph 509 ♥apache-2.0Updated 58 days ago

    drbaph/MiniMax-H3-Turbo-Lora-ComfyUI
  4. Official Le Scribe Audio MCP server: search, read, summarize & code French audio transcripts.

    Stale Official MCP Registry, io.github.zoulouzaza76 Updated 6 days ago 1 note

  5. Transcribe any audio or video URL to text, SRT and VTT, with chunking and only-new episodes

    Stale Official MCP Registry, io.github.pavel-tashev Updated 56 days ago 1 note

  6. Whisper speech to text, 99 languages: files, TikTok and podcast links to text, SRT, Word/PDF.

    Stale Official MCP Registry, io.github.fernandoguiraud16-coder Updated 26 days ago 1 note

  7. Transcribe audio and video from a link or local file into text and SRT subtitles. Pay-as-you-go.

    Stale Official MCP Registry, com.useears Updated 14 days ago 1 note

  8. Transcribes audio and video files to text, SRT, VTT and timestamped chunks for RAG.

    Stale Official MCP Registry, io.github.BrunenJere Updated 12 days ago 1 note

  9. Transcribe audio and video file URLs to text, SRT and VTT with Whisper via Apify, per audio minute.

    Stale Official MCP Registry, com.ctriolab Updated 6 days ago 1 note

  10. image text to video model by VideoRebirthAI · minimax-h3

    Indexed Hugging Face Hub, VideoRebirthAI 317 ♥otherUpdated 2 days ago

    VideoRebirthAI/hyperflow-h3-flash
  11. image to video model by Pika-Labs · minimax-h3

    Indexed Hugging Face Hub, Pika-Labs 197 ♥otherUpdated 17 days ago

    Pika-Labs/Pika-H3-Flex-Turbo-LoRA
  12. text to video model by Veda-Sparse · minimax-h3

    Stale Hugging Face Hub, Veda-Sparse 111 ♥otherUpdated 42 days ago

    Veda-Sparse/Minimax-H3-T2VA-Veda-8NFE-600Step-Preview
  13. Transcribe every audio or video link in a list: plain text, or speakers, timestamps and SRT

    Stale Official MCP Registry, io.github.Nero-Engine Updated 45 days ago 1 note

  14. clef-omni

    Models

    image text to text model by Cloudflare · transformers

    Stale Hugging Face Hub, Cloudflare 135 ♥apache-2.0Updated 28 days ago

    Cloudflare/clef-omni
  15. image to video model by akhaliq · minimax-h3

    Stale Hugging Face Hub, akhaliq 79 ♥otherUpdated 17 days ago

    akhaliq/Pika-H3-Flex-Turbo-LoRA
  16. model by lightx2v · minimax-h3

    Stale Hugging Face Hub, lightx2v 92 ♥Updated 18 days ago

    lightx2v/MiniMax-H3-Prompt-Rewriter-Qwen3.8-27B-Ref2VA
  17. text to video model by Veda-Sparse · minimax-h3

    Stale Hugging Face Hub, Veda-Sparse 38 ♥otherUpdated 39 days ago

    Veda-Sparse/Minimax-H3-R2VA-Veda-Preview
  18. image text to video model by BennyDaBall · minimax-h3

    Indexed Hugging Face Hub, BennyDaBall 35 ♥otherUpdated yesterday

    BennyDaBall/HyperFlow-H3-Flash-INT8-ComfyUI
  19. api.clarify.io

    Public APIs

    The API to Search and Understand Audio & Video Data.

    Indexed APIs.guru OpenAPI Directory, clarify.io Updated 7 years ago

  20. CloudConvert

    Public APIs

    Online file converter for audio, video, document, ebook, archive, image, spreadsheet, presentation

    Indexed public-apis (GitHub list)

  21. mcp

    MCP servers

    Convert, compress, resize and trim images, audio, video and PDFs from local paths.

    Stale Official MCP Registry, app.formatika Updated 3 months ago 2 notes

    @formatika/mcp@0.1.2
  22. Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

    Indexed OpenRouter model list, qwen Updated 56 days ago

    qwen/qwen3.8-omni-flash
  23. Parlova

    MCP servers

    Transcribe local audio/video and YouTube into timestamped, speaker-labelled text. 90+ languages.

    Stale Official MCP Registry, io.github.fort652 Updated 5 days ago 2 notes

    parlova@1.0.1
  24. transcribe

    MCP servers

    Transcribe audio & video to text for AI agents: 100+ languages, speaker labels, webhooks.

    Stale Official MCP Registry, com.transcribevideototext Updated 4 months ago 1 note

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.