Media Generation

Disclaimer

This specific page uses temporary drafts written and maintained by Generative AI. While verified to be accurate, please cross-verify with source code.

TomoriBot can create media right inside chat: images, short videos, and spoken voice messages. Ask her in plain language (“draw me a…”, “send that as a voice message”) or use the /generate commands. Which capabilities are available depends on your configured provider; see Providers & Models.

Image GenerationText-to-image and image-to-image, with reference images from attachments, avatars, stickers, and emojis.

Video GenerationShort text-to-video and image-to-video clips with customizable aspect ratios.

Voice: TTS & STTNative Discord voice messages (text-to-speech) and audio transcription (speech-to-text).

Not every provider supports every capability. Local generation (ComfyUI, local voice servers) is available on self-hosted instances; see Self-Hosting.