50 AI Tools. One Conversation.

project_create

Create a new project from source video

project_open

Open existing project

project_list

List all projects with status filter

project_status

Detailed pipeline progress and disk usage

project_delete

Delete project, optionally preserve source

ingest

Run full 22-stage analysis pipeline

get_transcript

Paginated transcript with word-level timestamps

get_frame

Get frame with full moment context (inline image)

search_content

Semantic or text search across video content

find_best_moments

Purpose-aware scoring (hook, highlight, CTA, tutorial)

find_cut_points

Natural edit boundaries with convergence scoring

get_narrative_flow

Analyze narrative coherence of proposed segments

find_safe_cuts

Audio-safe cut points across entire video

create_edit

Create edit from EDL spec with auto-captions

modify_edit

Deep-merge changes with auto-versioning

auto_trim

Remove filler words and long pauses

color_adjust

Brightness, contrast, saturation, gamma, hue

add_motion

Zoom, pan, Ken Burns effects

add_overlay

Lower thirds, title cards, logos, CTAs

edit_history

Version history for an edit

revert_edit

Revert to previous version

apply_feedback

Natural language feedback to EDL changes

branch_edit

Fork edit for platform variants

list_branches

List all branches of an edit

render

Platform-optimized video with NVENC acceleration

get_editing_context

All editing data in one call

analyze_frame

Detect content regions and webcam PIP

preview_clip

2-5s 540p preview, no credits

inspect_render

Extract frames, probe metadata, quality checks

preview_layout

Single frame canvas layout preview

get_scene_map

Scene boundaries, faces, layouts, transcript

preview_segment

Low-quality segment preview, no credits

generate_music

AI music via ACE-Step or MusicGen

compose_midi

12 presets rendered to WAV via FluidSynth

generate_sfx

13 programmatic DSP sound effects

audio_cleanup

Noise reduction, de-hum, de-ess, normalization

auto_music

Video-aware automatic music generation

compose_music

Natural language to MIDI composition

prepare_voice_data

Extract and prepare voice training data

voice_profiles

Manage voice profiles with speaker embeddings

speak

TTS with iterative multi-gate verification

speak_optimized

Best-of-N candidate selection

lip_sync

LatentSync 1.6 diffusion lip-sync

extract_webcam

Extract webcam region as driver video

generate_video

End-to-end voice + lip-sync from text

disk_status

Storage tier breakdown

disk_cleanup

Free space by tier priority

config_get

Get configuration value

config_set

Set and validate configuration

config_list

List all configuration values