global/youtube-studio

YouTube Studio — composed pipeline for full video publishing prep.

Category: global
Source: workflows/youtube/studio.py

Input Schema

Field	Type	Default	Description
`media_path`	`object`	—
`media_url`	`object`	—
`regenerate`	`object`	—	When set, this run is a regeneration. Workflows may read `direction` / `keep` / `extra_instructions` to modulate prompts; the engine persists `parent_run_id` and `parent_variant_index` as run lineage columns.
`url`	`object`	—
`variants`	`integer`	`1`	Number of independent variant executions (1–10). When > 1, the engine runs the workflow N times with different sampling, producing N outputs.
`video_path`	`object`	—
`video_url`	`object`	—

Output Schema

No schema defined.

Task Pipeline

download_media → transcribe_audio → generate_titles → refine_title → generate_thumbnail → merge_titles_thumbnails → generate_description → collect_studio_output

Task	Description
`download_media`	Download video/audio from a URL or copy from a local path.
`transcribe_audio`	Transcribe media — delegates to SDK stage (Whisper word-level timestamps).
`generate_titles`	Generate 10 viral title options using Gemini.
`refine_title`	Refine the selected title based on optional user feedback.
`generate_thumbnail`	Generate thumbnails — delegates to SDK stage.
`merge_titles_thumbnails`	Merge parallel title-generation and thumbnail-generation results.
`generate_description`	Generate a YouTube description with chapters, SEO keywords, and CTAs.
`collect_studio_output`	Assemble all YouTube Studio outputs.

Run-spec example

Save the YAML below as my-run.yaml, edit the values, and run with the CLI or POST it to the API. Required fields are uncommented; optional knobs are documented above the input: block — copy any line under input: and uncomment to set.

workflow: global/youtube-studio

# Optional fields — copy any line(s) under `input:` and uncomment to set:
#   media_path: null
#
#   media_url: null
#
#   url: null
#
#   video_path: null
#
#   video_url: null
#

input: {}

Run it locally:

fab-workflow --from-file my-run.yaml

Or submit over the wire — the same file is the request body:

curl -X POST 'https://gofabric.dev/v1/workflows/runs?name=global/youtube-studio' \
  -H 'Authorization: Bearer fab_xxx' \
  -H 'content-type: application/yaml' \
  --data-binary @my-run.yaml

Every workflow also accepts the universal WorkflowInput fields — variants (1–10 fan-out) and regenerate (creative-direction hints with run lineage). See Run-specs (YAML / TOML / JSON) for the full top-level shape (metadata, priority, bundle, parent, etc.).

Warnings

Last user task collect_studio_output has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.
Task generate_thumbnail has no Pydantic types — contract is opaque to consumers.
Task merge_titles_thumbnails has no Pydantic types — contract is opaque to consumers.