This release adds 6 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+1 more
Summary
AI summaryAdds DaVinci Resolve 21.0 scripting‑API additions including AI audio classification, IntelliSearch analysis, slate detection, motion‑blur removal, speaker‑detection transcription and speech generation.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds DaVinci Resolve 21.0 scripting-API additions. Adds DaVinci Resolve 21.0 scripting-API additions. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds `perform_audio_classification` and `clear_audio_classification` actions on folder/media_pool_item tools. Adds `perform_audio_classification` and `clear_audio_classification` actions on folder/media_pool_item tools. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds `analyze_for_intellisearch` action with optional face identification. Adds `analyze_for_intellisearch` action with optional face identification. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds `analyze_for_slate` action for slate/clapboard detection with marker color option. Adds `analyze_for_slate` action for slate/clapboard detection with marker color option. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds `remove_motion_blur` action to render motion‑deblurred copies (creates new media files). Adds `remove_motion_blur` action to render motion‑deblurred copies (creates new media files). Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds `use_speaker_detection` optional boolean to `transcribe_audio` (Resolve 21+). Adds `use_speaker_detection` optional boolean to `transcribe_audio` (Resolve 21+). Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds `project_settings(action="generate_speech", ...)` wrapper for AI text‑to‑speech. Adds `project_settings(action="generate_speech", ...)` wrapper for AI text‑to‑speech. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Adds `resolve_control(action="disable_background_tasks_for_current_session")` to quiet background tasks. Adds `resolve_control(action="disable_background_tasks_for_current_session")` to quiet background tasks. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Feature | Medium |
Updates `media_analysis` report and `resolve.ai_features` payload to list available 21.0 AI methods and required Extras. Updates `media_analysis` report and `resolve.ai_features` payload to list available 21.0 AI methods and required Extras. Source: llm_adapter@2026-06-05 Confidence: high |
— |
| Bugfix | Low |
Fixes v2.28.1 transcription bug. Fixes v2.28.1 transcription bug. Source: llm_adapter@2026-06-05 Confidence: high |
— |
Full changelog
Adds the DaVinci Resolve 21.0 scripting-API additions. Every new method is runtime-detected, so the tools stay inert on older Resolve builds and activate automatically on Resolve 21+. Method names were validated live against Resolve Studio 21.0.0.47.
New AI analysis actions
On the folder and media_pool_item compound tools (mirrored as granular --full tools):
perform_audio_classification/clear_audio_classification— classify clip audio into categories and subcategories.analyze_for_intellisearch(identify_faces?, is_better_mode?)— IntelliSearch analysis with optional face identification. Requires the AI IntelliSearch Extra.analyze_for_slate(marker_color?)— slate/clapboard detection that drops a marker of the chosen color (validated against the 16 Resolve marker colors). Requires the AI Slate ID Extra.remove_motion_blur(deblur_option?)— renders motion-deblurred copies. Creates new media files (source media is never modified) and is confirm-token gated.
Speaker-detection transcription
transcribe_audio now accepts an optional use_speaker_detection boolean (Resolve 21+); omit it to use the project's Speech Recognition setting.
Speech generation
project_settings(action="generate_speech", ...) wraps Project.GenerateSpeech (AI text-to-speech). Creates a new audio item and optionally places it on the timeline, so it is also confirm-token gated. Requires the AI Speech Generator Extra.
Session control
resolve_control(action="disable_background_tasks_for_current_session") quiets background work during heavy scripted runs.
Capability surface
The media_analysis transcription-capability report and the control panel boot payload (resolve.ai_features) now list which 21.0 AI methods are available and which Extras each gated method needs.
Notes: these are Resolve-local GPU/AI operations and do not consume the Claude-side analysis token budget, so they are not metered by the analysis-caps layer; the derivative-creating ones are protected by the confirm-token gate instead. The granular --full server grew from 329 to 341 tools.
Also includes the v2.28.1 transcription bug fix.
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
Related context
Beta — feedback welcome: [email protected]