Skip to content

youtube/descriptions

Auto Description Generation — with chapter timestamps from Whisper transcript.

Category: youtube
Source: workflows/youtube/descriptions.py

FieldTypeDefaultDescription
full_textstring""
regenerateobjectWhen 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.
selected_titleobject
topicstring""
transcriptany[]
variantsinteger1Number of independent variant executions (1–10). When > 1, the engine runs the workflow N times with different sampling, producing N outputs.

No schema defined.

generate_description
TaskDescription
generate_descriptionGenerate a YouTube description with chapters, SEO keywords, and CTAs.

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: youtube/descriptions
# Optional fields — copy any line(s) under `input:` and uncomment to set:
# full_text: ""
#
# selected_title: null
#
# topic: ""
#
# transcript: []
#
input: {}

Run it locally:

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

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

Terminal window
curl -X POST 'https://gofabric.dev/v1/workflows/runs?name=youtube/descriptions' \
-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.).

  • Last user task generate_description has no Pydantic return type — workflow output schema is null. Declare a WorkflowOutput subclass and pass it to Flow(output=…) for a strict contract.