video/quick-shorts

Quick shorts — lightweight faceless video from topic or script.

Category: video
Source: workflows/video/quick_shorts.py

Input Schema

Field	Type	Default	Description
`background`	`string`	`"ai"`	Background video source: ‘ai’ (AI-generated from script, requires broll model in quality profile), ‘random’ (gaming/satisfying footage), ‘stock’ (Pexels), or ‘solid’ (plain color).
`bgm`	`boolean`	`false`	Add background music (off by default to stay cheap).
`bgm_volume`	`number`	`0.12`	Background music volume (0.0–1.0) when bgm is enabled.
`duration_secs`	`integer`	`30`	Target script duration in seconds (only used when generating a script from topic).
`language`	`string`	`"en"`	Script / TTS language code.
`quality`	`string`	`"cheap"`	SDK quality profile: ‘free’, ‘budget’, ‘cheap’, ‘standard’, ‘premium’, ‘local’. Controls model selection for TTS, script, etc.
`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.
`script_text`	`string`	`""`	Explicit narration text. Skips script generation when set.
`subtitle_style`	`string`	`"karaoke"`	Subtitle preset: ‘karaoke’, ‘word’, or ‘sentence’.
`subtitles`	`boolean`	`true`	Burn karaoke-style captions onto the video.
`topic`	`string`	`""`	Video topic — a script is auto-generated from this. Ignored when script_text is provided.
`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.
`voice_id`	`string`	`""`	Explicit TTS voice ID. Takes precedence over voice_style.
`voice_style`	`string`	`""`	Descriptive voice style (e.g. ‘warm female’, ‘deep narrator’).

Output Schema

Field	Type	Default	Description
`asset_id`	`object`	—	Fabric asset ID (when server access is available).
`duration`	`number`	`0.0`	Duration of the final video in seconds.
`kind`	`object`	—	Variant card shape: video / carousel / image / text. Surfaced on the per-variant entry of the run-output API and used by gallery UIs to pick the right layout.
`script_text`	`string`	`""`	The narration text that was spoken.
`upgrade_input`	`object`	—	Pre-built input for submitting to video/ai-shorts with the same script.
`video_path`	`string`	required	Path to the final MP4.

Task Pipeline

prepare_input → generate_voiceover → generate_background → merge_branches → compose_video → add_subtitles → add_bgm → collect_output

Task	Description
`prepare_input`	Validate input and generate script if needed.
`generate_voiceover`	Generate TTS voiceover — reuses SDK voiceover stage.
`generate_background`	Generate per-segment AI video clips, or fall back to catalog/stock.
`merge_branches`	Merge parallel voiceover + background branches.
`compose_video`	Compose per-segment video clips with voiceover.
`add_subtitles`	Burn karaoke subtitles if enabled.
`add_bgm`	Generate and mix background music if enabled.
`collect_output`	Persist artifact, build upgrade payload, and return output.

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: video/quick-shorts

# Optional fields — copy any line(s) under `input:` and uncomment to set:
# Background video source: 'ai' (AI-generated from script, requires broll model in quality profile), 'random' (gaming/satisfying footage), 'stock' (Pexels), or 'solid' (plain color).
#   background: ai
#
# Add background music (off by default to stay cheap).
#   bgm: false
#
# Background music volume (0.0–1.0) when bgm is enabled.
#   bgm_volume: 0.12
#
# Target script duration in seconds (only used when generating a script from topic).
#   duration_secs: 30
#
# Script / TTS language code.
#   language: en
#
# SDK quality profile: 'free', 'budget', 'cheap', 'standard', 'premium', 'local'. Controls model selection for TTS, script, etc.
#   quality: cheap
#
# Explicit narration text. Skips script generation when set.
#   script_text: ""
#
# Subtitle preset: 'karaoke', 'word', or 'sentence'.
#   subtitle_style: karaoke
#
# Burn karaoke-style captions onto the video.
#   subtitles: true
#
# Video topic — a script is auto-generated from this. Ignored when script_text is provided.
#   topic: ""
#
# Explicit TTS voice ID. Takes precedence over voice_style.
#   voice_id: ""
#
# Descriptive voice style (e.g. 'warm female', 'deep narrator').
#   voice_style: ""
#

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=video/quick-shorts' \
  -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

Task generate_voiceover has no Pydantic types — contract is opaque to consumers.
Task merge_branches has no Pydantic types — contract is opaque to consumers.