Skip to content
Auteryn

Multi-Modal Content Generation

Auteryn agents can produce images, video, audio, slide decks and diagrams as well as text. Each needs its capability on under the agent’s Capabilities, such as Image generation or Presentations.

What you can generate

Section titled “What you can generate”

Images

Text-to-image. The agent picks a tier for each image, from lite (1K, quickest and cheapest) through standard (up to 2K) to pro (up to 4K, Pro and up).

Videos

Text-to-video with native audio. Generate a clip, extend it, or edit one the agent already made. Internal agents on Pro and up, with strict per-run and per-day limits.

Presentations

Slide decks built as structured data: create, edit, export, and publish them without a sandbox.

Diagrams & charts

D2/Python diagrams and UI artifacts (charts, tables, documents) emitted as artifacts in the workspace.

Image generation

Section titled “Image generation”
  • Available to Internal and customer-facing agents once Image generation is on
  • Image tiers: the agent picks one per image. The lite tier is the quickest and cheapest, at 1K. The standard tier is the default, up to 2K. The pro tier goes up to 4K and needs Pro and up. It costs the same as standard up to 2K and more at 4K. Each tier bills at its own rate; see Pricing.
  • Configurable aspect ratios and output resolution; outputs appear as artifacts in the workspace
  • Rate limits apply per run and per hour (the pro tier has a tighter per-run cap)

Example instruction:

Generate a hero image for our product launch: modern tech aesthetic,
blue gradient, abstract shapes. Use 16:9 aspect ratio.

Video generation

Section titled “Video generation”

Video uses Gemini Omni Flash (gemini-omni-1.1-flash). Every clip comes back as an MP4 with its own audio track — ambience, music, or spoken dialogue you asked for in the prompt.

The agent can do three things with video:

Action What it does
Generate One 3–10 second beat from a prompt. The model decides the exact length; you choose the resolution (360p, 720p, 1080p, 4k) and the aspect ratio (16:9 or 9:16).
Extend Continues a clip the agent just made, 10 seconds at a time, to a 40-second total.
Edit Adds or removes an object, restyles, or relights — either a clip the agent generated or one you attached to the conversation.
  • Steer the look with up to 3 reference images, or supply a first and last frame and let the model interpolate the motion between them
  • Available on Pro and up. A run can make up to 6 video actions and 40 seconds of video. Each organization can make 10 clips a day on Pro or 50 on Business, with a daily cap on total generated seconds (see Pricing)
  • The agent confirms the estimated cost with you before rendering, and progress streams live in the workspace while it renders
  • Every generated video is marked as AI-generated

Presentations

Section titled “Presentations”

Presentations work without a sandbox. The agent builds the deck and edits it slide by slide. From there you can add narration and download the deck as PDF or PowerPoint. You can also share it as a video or publish it to a shareable link.

For the full lifecycle — generate, refine, narrate, export, and publish — see the Presentations deep dive.

Diagrams & artifacts

Section titled “Diagrams & artifacts”
  • D2 / Python diagrams — rendered in a short-lived container of their own, separate from the agent’s sandbox
  • Artifacts — charts, tables, markdown documents and HTML, streamed to the workspace as artifacts

Audio

Section titled “Audio”

Agents can also generate audio — text-to-speech narration and voiceover, and multi-speaker podcast-style conversations. Outputs upload to cloud storage and appear as playable artifacts. Speech costs 50 credits per 1,000 characters in a preset, designed or cloned voice, and 60 in a voice cloned before the consent line was added, per the pricing page.

For the full breakdown — including how audio differs from real-time Voice conversations — see the Audio generation deep dive.

Tips

Section titled “Tips”
  • Switch on the capability you need under Capabilities before asking for images, video or audio
  • Be specific about style, aspect ratio, and brand constraints in instructions
  • Review generated media before publishing — models can misinterpret prompts
  • Video generation is slow and credit-intensive; iterate at 360p and only render the final shot at 720p or above
Section titled “Related”