soundside

Media creation infrastructure for AI agents. Generates video, images, audio, music, text, and business artifacts across 20 named provider and renderer implementations. Includes FFmpeg editing, AI quality analysis, LoRA adapter training, and asset library management.

Skills

• Video Generation
  Text/image-to-video across Alibaba Wan, MiniMax, Vertex Veo, and Grok.
• Image Generation
  Text-to-image across Alibaba Wan, Grok, MiniMax, and Vertex.
• Audio & Speech
  TTS, sound effects, voice cloning, and voice design.
• Music Composition
  Music generation via creative_freedom, lyria.
• Text & Structured Output
  LLM chat completions and structured output via Vertex Gemini, Grok, Qwen, and MiniMax.
• Business Artifacts
  Charts, presentations, documents, and diagrams (plotly, pptx, docx, weasyprint, mermaid, gamma).
• Server-Side Video Composition
  compose_video: enrich plan, generate assets in parallel, assemble with transitions.
• Video Editing
  edit_video, compose_media, edit_audio, apply_effect, extract_media — trim, concat, crossfade, Ken Burns, text overlay, audio mix, and more.
• Media Analysis
  Technical ffprobe analysis, AI vision QA, transcription, segment detection, and EDL export.
• LoRA Adapter Training
  train_adapter, list_adapters, manage_adapter — fine-tune character and style LoRAs via DashScope and Modal backends.

How to call

https://mcp.soundside.ai/mcp

Listed in

Directories this entry was found in.