stealthstack.ai Status Publish a catalog

AI media generation

Resources that make or edit media with AI models.

They cover image, video, music, voice and 3D generation, avatars, and transcription and text to speech.

Listings are what publishers declare in their ARD catalogs and the registries StealthStack reads. The category and summaries are our reading of each listing. Each listing links to its own page with the publisher's endpoint.

All types MCP serversSkillsA2A agentsAPIs
Image generationVideo generationAudio and voiceMusicTranscription and TTS3D generation
  1. SKILLrunway Zapier connector skill for Runway: generate and edit AI images, video and audio.
  2. SKILLheygen Zapier connector skill for HeyGen: AI avatar videos, translation, lip-sync and voices.
  3. SKILLspeech Skill for text-to-speech narration and voiceover via the OpenAI Audio API.
  4. A2A AGENToverlayr TikTok-style caption rendering to MP4; $0.10 USDC per render via x402.
  5. SKILLelevenlabs Zapier connector skill for ElevenLabs: TTS, sound effects, transcription and voices.
  6. SKILLParakeet TDT 0.6b V3 Transcribes audio to text with timestamps using NVIDIA Parakeet.
  7. SKILLimagegen Skill for generating or editing raster images with AI.
  8. SKILLYuE2-3B Music Generator Generates songs from style prompts and structured lyrics with YuE2-3B.
  9. SKILLF5-TTS Generates speech in a custom voice from a reference audio clip.
  10. SKILLSeed Voice Conversion Converts a voice to match another speaker with Seed-VC.
  11. SKILLDia 1.6B Generates spoken dialogue audio from text with an optional voice prompt.
  12. SKILLFLUX.2 Klein 9B KV Generates or edits images from text and optional photos with FLUX.2 Klein.
  13. MCP SERVERBibiGPT Video & Audio MCP Server Summarizes, transcribes and chats with video and podcast content; OAuth.
  14. MCP SERVERFLUX.2 Klein 9B KV MCP Server MCP server to generate or edit images with FLUX.2 Klein 9B.
  15. SKILLMedia Transcription Skill to transcribe audio or video files via Ausca's metered service.
  16. APIDeepgram via MPP Deepgram transcription and text-to-speech as a pay-per-request MPP service.
  17. MCP SERVERmcp-listen Offline microphone capture and speech-to-text for agents; audio stays local.
  18. SKILLgenerate-image Skill for generating images with OpenAI or Gemini models; needs a provider API key.
  19. MCP SERVERjellypod Creates and manages podcasts, episodes, videos, shorts and voiceovers in Jellypod.
  20. A2A AGENTBibiGPT AI Video & Audio Assistant A2A agent that summarizes and transcribes video and audio URLs.
  21. SKILLKokoro TTS Generates natural-sounding speech from text with Kokoro TTS.
  22. MCP SERVERaudio-transcribe-long Transcribes 15-30 minute audio from a public URL with OpenAI Whisper.
  23. APIMagic Hour API Magic Hour API for AI video, image and audio projects.
  24. SKILLAuK Generates AI voice audio from text and reference clips.
  25. SKILLspeak-summary Skill converting text or summaries into MP3 with local CPU text-to-speech.
  26. SKILLOmniVoice Generates speech from text with optional voice cloning.
  27. SKILLnemotron-speech Skill routing Nemotron Speech NIM tasks: deploy and test ASR, TTS and NMT.
  28. SKILLMiniMax H3 Turbo LoRA Generates AI videos from prompts and images with MiniMax H3 Turbo LoRA.
  29. SKILLazure-ai-transcription-py Skill for real-time and batch speech-to-text with the Azure AI Transcription SDK.
  30. SKILLAgents Skill for building voice AI agents with ElevenLabs.
  31. SKILLazure-speech-to-text-rest-py Skill for short-audio speech recognition with the Azure Speech to Text REST API.
  32. API2s.io Transcribe Transcribes an audio file to text; pay per call via x402 USDC.
  33. APIBibiGPT REST API (OpenAPI) BibiGPT REST API with OpenAI-compatible chat over video, plus transcription.
  34. SKILLpodcast-generation Skill generating podcast-style audio via Azure OpenAI GPT Realtime Mini.
  35. SKILLCLIP Interrogator Generates text prompts describing any input image using CLIP.
  36. SKILLnemotron-voice-agent-builder Skill building NVIDIA real-time voice agents with Pipecat or LiveKit.
  37. APIAI Content Drop REST API (v1) REST API to generate AI video and images and poll jobs; flat credit costs.
  38. SKILLAI Content Drop agent skills Skill guides for AI video prompting, UGC ad scripts and model selection by budget.
  39. A2A AGENTArgonautWorks Product Image API Generates a 768x768 product, landscape or still-life image via local inference; x402.
  40. APISpeko Relay API OpenAPI contract for Speko's hosted STT, LLM and TTS relay.
  41. MCP SERVERVend YouTube Transcript (x402, Nano) Fetches YouTube video transcripts with timestamps; 0.0005 XNO via x402.
  42. SKILLJoy Caption Alpha Two Generates detailed captions or prompts for any image with JoyCaption.
  43. SKILLazure-ai-voicelive-dotnet Skill for real-time voice AI apps with the Azure Voice Live SDK for .NET.
  44. SKILLazure-ai-voicelive-ts Skill for real-time voice AI apps with the Azure Voice Live JavaScript SDK.

Related categories

Design and creativeEngineering and hardware All categories