feat(editor): imported audio, and transcript words you can correct, add and delete

.gitignore

@@ -132,3 +132,4 @@ workbench/fixtures/
 /aur_ci
 /aur_ci.pub
 /aur_known_hosts
+tmp_handoff.md

crates/compositor/src/pipeline_linux.rs

@@ -27,7 +27,7 @@ use std::ffi::CString;
 use std::ptr;
 
 use crate::audio::{
-    assemble_concatenated_pcm, build_audio_concat_plan, finish_audio,
+    assemble_concatenated_pcm, build_audio_concat_plan, finish_audio, mix_external_tracks,
     AacEncoder, PlanarPcm,
 };
 use crate::audio_jobs::{decode_and_stretch_clip_audio, ClipAudioJobs};
@@ -1002,6 +1002,12 @@ pub fn run_composited_multi(
 
     let scene = comp.scene_snapshot();
     let audio_settings = scene.as_ref().map(|scene| scene.audio).unwrap_or_default();
+    // Imported audio tracks (issue #350), cloned out of the borrowed scene so the
+    // mix step below owns them. Empty for a project with no imported audio.
+    let audio_tracks = scene
+        .as_ref()
+        .map(|scene| scene.audio_tracks.clone())
+        .unwrap_or_default();
     // Ring de staging a 2 : l'export ne veut que du debit, une frame de latence
     // ne se voit pas dans un fichier. Voir `Compositor::set_readback_depth` pour
     // la raison pour laquelle la preview, elle, reste a 1.
@@ -1190,7 +1196,10 @@ pub fn run_composited_multi(
         let plan = build_audio_concat_plan(&clip_frame_counts, &declared_audio, out_fps as f64);
         let octx = mux.octx;
         mux.aac.encode(
-            &finish_audio(assemble_concatenated_pcm(&clip_pcm, &plan), audio_settings),
+            &finish_audio(
+                mix_external_tracks(assemble_concatenated_pcm(&clip_pcm, &plan), &audio_tracks),
+                audio_settings,
+            ),
             octx,
         )?;
         mux.finish()?;

crates/compositor/src/pipeline_macos.rs

@@ -30,7 +30,7 @@
 //! décodeurs, symétrique.
 
 use crate::audio::{
-    assemble_concatenated_pcm, build_audio_concat_plan, finish_audio,
+    assemble_concatenated_pcm, build_audio_concat_plan, finish_audio, mix_external_tracks,
     AacEncoder, PlanarPcm,
 };
 use crate::audio_jobs::{decode_and_stretch_clip_audio, ClipAudioJobs};
@@ -1172,6 +1172,11 @@ pub fn run_composited_multi(
     // raconte avoir déjà coûté une fois.
     let scene = comp.scene_snapshot();
     let audio_settings = scene.as_ref().map(|scene| scene.audio).unwrap_or_default();
+    // Imported audio tracks (issue #350), cloned out of the borrowed scene.
+    let audio_tracks = scene
+        .as_ref()
+        .map(|scene| scene.audio_tracks.clone())
+        .unwrap_or_default();
     frames = unsafe {
         crate::timeline_walk::walk_composited_timeline(
             clips,
@@ -1247,7 +1252,10 @@ pub fn run_composited_multi(
         let declared_audio: Vec<bool> = clips.iter().map(|clip| clip.has_audio).collect();
         let plan = build_audio_concat_plan(&clip_frame_counts, &declared_audio, out_fps as f64);
         audio_encoder.encode(
-            &finish_audio(assemble_concatenated_pcm(&clip_pcm, &plan), audio_settings),
+            &finish_audio(
+                mix_external_tracks(assemble_concatenated_pcm(&clip_pcm, &plan), &audio_tracks),
+                audio_settings,
+            ),
             octx,
         )?;
 

crates/compositor/src/pipeline_windows.rs

@@ -3,7 +3,7 @@
 //! tout le run, deux lectures seulement. Rien dans la boucle ne peut fausser le fps.
 
 use crate::audio::{
-    assemble_concatenated_pcm, build_audio_concat_plan, finish_audio,
+    assemble_concatenated_pcm, build_audio_concat_plan, finish_audio, mix_external_tracks,
     AacEncoder, PlanarPcm,
 };
 use crate::audio_jobs::{decode_and_stretch_clip_audio, ClipAudioJobs};
@@ -1351,6 +1351,11 @@ unsafe fn run_multi_inner(
     // fenêtrage par clip ; `walk_composited_timeline` s'en charge.
     let scene = comp.scene_snapshot();
     let audio_settings = scene.as_ref().map(|scene| scene.audio).unwrap_or_default();
+    // Imported audio tracks (issue #350), cloned out of the borrowed scene.
+    let audio_tracks = scene
+        .as_ref()
+        .map(|scene| scene.audio_tracks.clone())
+        .unwrap_or_default();
 
     // ---- encodeur (choisi à l'exécution, cf. ExportCodec::candidates) + mux ----
     // Backend CPU : pas de pool D3D11 du tout. `av_hwdevice_ctx_init(D3D11VA)` échoue sur
@@ -1484,7 +1489,7 @@ unsafe fn run_multi_inner(
         out_fps as f64,
     );
     let assembled_audio = finish_audio(
-        assemble_concatenated_pcm(&clip_pcm, &audio_plan),
+        mix_external_tracks(assemble_concatenated_pcm(&clip_pcm, &audio_plan), &audio_tracks),
         audio_settings,
     );
     audio_encoder.encode(&assembled_audio, octx)?;

crates/compositor/src/scene.rs

@@ -432,6 +432,39 @@ pub struct SceneAudio {
     pub gain_db: f32,
 }
 
+/// One imported audio track (issue #350) mixed over the assembled programme —
+/// voiceover / BGM / SFX. Deliberately a SEPARATE `Scene` field rather than a
+/// member of `SceneAudio`, so `SceneAudio` stays `Copy` and the pipelines keep
+/// copying it out of a borrow unchanged.
+///
+/// `start_sec` is the track's head on the OUTPUT programme; `trim_start_sec` /
+/// `trim_end_sec` window the source file (both source seconds). The renderer
+/// resolves `start_sec` from the track's raw timeline position — equal to it when
+/// the project has no trims/speed, which is the case this first cut mixes exactly.
+#[derive(Debug, Clone, Default, Deserialize)]
+#[serde(rename_all = "camelCase")]
+pub struct SceneAudioTrack {
+    pub path: String,
+    #[serde(default)]
+    pub start_sec: f64,
+    #[serde(default)]
+    pub gain_db: f32,
+    #[serde(default)]
+    pub trim_start_sec: f64,
+    #[serde(default)]
+    pub trim_end_sec: Option<f64>,
+    /// Ramp lengths at this entry's own edges, in seconds. The app puts them only
+    /// on the pieces that touch the track's real start and end, so a split or
+    /// looping track fades once instead of at every cut or repeat.
+    ///
+    /// `#[serde(default)]` for the usual reason: a payload from a build that
+    /// predates the field must degrade to "no fade", not fail the whole scene.
+    #[serde(default)]
+    pub fade_in_sec: f64,
+    #[serde(default)]
+    pub fade_out_sec: f64,
+}
+
 #[derive(Debug, Clone, Copy, Deserialize)]
 #[serde(rename_all = "camelCase")]
 pub struct SceneOutput {
@@ -500,6 +533,10 @@ pub struct Scene {
     /// Global audio finishing. Default keeps old scene payloads bit-for-bit compatible.
     #[serde(default)]
     pub audio: SceneAudio,
+    /// Imported audio tracks mixed over the programme (issue #350). `#[serde(default)]`:
+    /// absent from every scene written before this, and from a project with none.
+    #[serde(default)]
+    pub audio_tracks: Vec<SceneAudioTrack>,
     /// Crop écran par clip, dans le même ordre que `clips` (`cropByClip` côté TS).
     #[serde(default)]
     pub crop_by_clip: Vec<Option<SceneCrop>>,
@@ -576,6 +613,9 @@ impl Scene {
 mod tests {
     use super::*;
 
+    /// lui. Sans ce défaut, ouvrir un projet fait par une version antérieure échouerait au
+    /// parse au lieu de simplement ne rien tenir (issue #560).
+
     #[test]
     fn parses_a_minimal_scene_json() {
         let json = r##"{

crates/compositor/src/timeline_walk.rs

@@ -17,6 +17,7 @@ use crate::compositor::Compositor;
 use crate::config::Cfg;
 use crate::cursor::CursorTrack;
 use crate::d3d::Gpu;
+use crate::ffi::AVFrame;
 use crate::frame_geometry::webcam_is_real;
 use crate::pipeline::{ClipSource, Decoder};
 use crate::regions::{speed_segments_for_window, SpeedSegment};
@@ -336,6 +337,7 @@ pub(crate) unsafe fn walk_composited_timeline(
                 frames += 1;
             }
         }
+
         on_clip_end(
             clip_index,
             source_end_sec,

crates/poc-d3d/src/bench.rs

@@ -150,6 +150,7 @@ fn run_bench(args: &[String]) -> Result<()> {
                 source_end_sec: 6.0, // la fixture entière (§ fixture.json : 6 s, 360 frames)
                 webcam_offset_sec: 0.0,
                 has_audio: false,
+                hold_sec: 0.0,
             };
             let path = format!("{out}/{}_{:?}.mp4", cfg.name, backend).to_lowercase();
             let s = pipeline::run_composited_multi(
@@ -292,6 +293,7 @@ fn run_gif_bench(
         source_end_sec: f64::MAX,
         webcam_offset_sec: 0.0,
         has_audio: false,
+        hold_sec: 0.0,
     }];
     for r in 0..repeat {
         // Each run writes to the same path — the last frame wins. The