Skip to content
Build Perch
Browse documentation

Generating media

Short answer: Ask the AI in any chat and it can generate images, speech, music, and video (including image-to-image and image-to-video) through OpenRouter’s hosted media models. Generation is OpenRouter-only: local Ollama and Ollama Cloud can chat, but they can’t generate media.

What can the AI generate?

Each of the four media types is a tool the AI calls mid-conversation (generate_image, generate_speech, generate_music, generate_video), and each one is backed by a model you can configure per chat, separately from the model you’re chatting with. Find them under the Models tab of Chat Configuration, as Image Generator, Speech Generator, Music Generator, and Video Generator rows. You don’t have to set any of them yourself; each one falls back to a low-cost default until you pick something else.

  • Images: text-to-image, saved as PNG. For image-to-image, attach, drag, or sketch an image onto your message (or point at one already in the workspace) and describe the change; the AI edits, restyles, or varies it instead of starting from a blank prompt.
  • Speech: text-to-speech. Each chat has a default voice; ask for a different one (“read that in a deeper voice”) and the AI passes it through as a one-off override.
  • Music: a description (genre, mood, instruments, tempo, and optional lyrics) becomes a track. It’s the slowest of the four and best-effort: if nothing comes back, ask again rather than expecting an automatic retry.
  • Video: text-to-video, and image-to-video: pass a starting image and the AI animates from it. Generation is asynchronous: the tool call returns immediately and the finished clip appears in the chat as a placeholder that turns into a player, usually within a few minutes. Only one video renders at a time app-wide; you can cancel from the bubble itself or from the Activity bar, and an in-progress job survives an app restart or a workspace switch.

Studio mode owns media generation by default, but any mode can reach for it mid-turn; you don’t need to switch modes just to ask for an image.

How do I generate media?

  1. Just ask: media generation works out of the box with a low-cost default model for each type. To pick a specific model instead, open Chat Configuration → Models and set the Image / Speech / Music / Video Generator row you want to change.
  2. Ask for what you want in plain language: “generate a picture of a lighthouse at sunset,” “turn this into a 9:16 vertical video,” “make a 30-second lo-fi track.” The AI calls the matching tool and the result renders inline in the chat.
  3. For image-to-image or image-to-video, attach or drag the source image onto your message first (or name a file already in the workspace), then describe the change.
  4. If tool approval is set to ask first, confirm the call; media generation shows the same plain-language approval banner as any other tool call.

Good to know

  • The chat itself has to be running on OpenRouter for these tools to show up at all; a chat on a local Ollama or Ollama Cloud model won’t offer image/speech/music/video generation, regardless of which media models you’ve configured under Models.
  • Agents and workflows can generate image, speech, and music too. Headless runs are held to a per-run and a per-day budget cap (default 50 generations/day, in Settings), because unattended generation spends real money on your OpenRouter key. Video generation is chat-only.
  • Generated files save automatically into the workspace’s BuildPerch folder (images to images/, speech and music to audio/, video to video/) and show up immediately in the matching gallery view. See Galleries & saving media.
  • Privacy Mode covers media generation the same way it covers chat: when it’s on, every media request also carries the zero-data-retention flag.
  • Media generation always needs OpenRouter. Editing media you already have (trimming, captioning, cleaning up audio) runs locally instead; see Local media editing.