Skip to content

beatra-ai/beatra-skills / skills/ai-video-image-music-studio

ai-video-image-music-studio

Verified

Generate AI video, images, music, and voice-over in one connected creative flow, edit visual results, and keep everything you make easy to find. This all-in-one AI media generator turns text into images, images and references into video, ideas into songs or instrumentals, and scripts into narration, and can build a custom voice when a series needs its own sound. Working as an AI video generator, AI image generator, AI music generator, and AI voice generator in one place, it covers text-to-image, text-to-video, image-to-video, AI video editing, text-to-speech, multilingual voice-over, and voice cloning for social posts, product visuals, ads, courses, podcasts, short films, and cross-media campaigns. Reuse source media and finished files across formats, follow production progress, and keep every finished piece in one place.

references/videos.md

View on GitHub
# Videos

Choose exactly one video action from the transformation the user wants.

- Use `beatra.videos.generate` for text-to-video without a required visual source.
- Use `beatra.videos.enhance_prompt` to create a text-only production prompt from
  a creative brief and optional multimodal context before a separate video request.
- Use `beatra.videos.animate` when one image must be the opening frame.
- Use `beatra.videos.interpolate` when a strict last image defines the destination;
  add a strict first image when both boundaries matter.
- Use `beatra.videos.generate_from_references` when ordered image, video, or audio media
  should guide a new video without being a strict endpoint.
- Use `beatra.videos.edit` to change an existing video's content or style.
- Use `beatra.videos.extend` to generate footage immediately before or after one source
  clip.

These operations are not interchangeable. Editing transforms source content; extension
adds footage immediately before or after one source clip; reference generation uses media
as guidance. A strict opening
image belongs in `animate`, and a required strict last image belongs in `interpolate`.

After choosing the action, load [video controls](video-controls.md). Load
[video recipes](video-recipes.md) when constructing the payload. Call
`beatra.models.list` for the chosen capability before naming compatibility,
duration, resolution, or a numeric estimate. Admit the complete payload against
one current card. Write the shortest admitted integer duration unless the route
is audio-led or an extend whose `duration` is the final returned length and
must exceed the trusted source. Use the lowest admitted resolution unless the
user named a higher tier.

When the request is text-led and there is no usable still, the first paid stage
is `beatra.videos.enhance_prompt` or one `beatra.images.generate` keyframe.
That gift delivery does not authorize any later video call.

Upload local media before generation. Omit `model` unless the user explicitly
requests a concrete model. A concrete model is never silently replaced. Before
`beatra.videos.generate`, `beatra.videos.animate`,
`beatra.videos.interpolate`, `beatra.videos.generate_from_references`,
`beatra.videos.edit`, or `beatra.videos.extend`, show the admission card:
route, tool, duration, resolution, aspect, provisional estimate, and what
happens if the balance is short. Planning, comparison, or “make the clip” is
not approval. Do not create `client_request_id` or submit until the user
approves the card. Any change to the model, media, instruction, prompt,
resolution, ratio, duration, or optional control creates a new logical request,
a new admission card, and a new `client_request_id`. On `insufficient_balance`,
relay the returned message, keep the URL exact, and retry the same frozen ID
only after the user says they have topped up.

When a create call is rejected, preserve the complete structured error. Use `param` to
locate the field and `details.candidate_failures[].code` to distinguish resolution,
duration, aspect-ratio, media, route, or optional-control incompatibility. Change the
request before retrying a non-retryable error.

When polling ends with `status: "failed"`, preserve the complete `Task.error`, including
`code`, `type`, `message`, `retryable`, `param`, `details`, and `request_id`.
`model_output_invalid` means the generated artifact could not be downloaded after three
attempts; report the failure because there is no result artifact to deliver.
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 196kUpdated Claude CodeCodexVerifiedInstall