Skip to content

Node-based terminal manager for AI coding agents — tmux-backed terminals and parallel agent sessions as draggable nodes on an infinite pan/zoom canvas. macOS, Linux, and a browser Server Edition.

docs(speech): the in-app delay is a separate bug, not the params

Dev Goswamie604504f4a7e
diff --git a/CLAUDE.md b/CLAUDE.md
index 0369261a6..4f7ad1e5e 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -9899,8 +9899,9 @@ Voice-to-text input captured via microphone, turned into terminal text via on-de
`gpu_device`, `flash_attn` and the rest were uninitialized stack memory and the result depended on
what was there. MEASURED on an M5 Pro, Electron 42, large-v3-turbo: the shipped binary crashed in 4
of 4 runs outside the app (`aheads_masks_init` then a crash in `whisper_free_state`, because garbage
- switched DTW on with large-v3's alignment heads) and took 7-10 s per dictation inside it; with the
- defaults it took 0.56 s for a 2.7 s clip and 0.93 s for 21 s, no crash. A newer whisper.cpp is
+ switched DTW on with large-v3's alignment heads); with the defaults it ran without a crash, 0.56 s
+ for a 2.7 s clip and 0.93 s for 21 s on Metal. The slow dictation inside the packaged app is a
+ separate bug: Metal cannot read its shaders inside app.asar. A newer whisper.cpp is
faster again (0.22 s / 0.43 s, measured the same way) but needs a build change on every platform;
that is a separate follow-up.
diff --git a/scripts/patch-smart-whisper.mjs b/scripts/patch-smart-whisper.mjs
index d4a5cd582..a3f841e98 100644
--- a/scripts/patch-smart-whisper.mjs
+++ b/scripts/patch-smart-whisper.mjs
@@ -35,8 +35,9 @@
* with DTW switched on by garbage, whisper_init_state() fails for large-v3-turbo ("tried to set
* alignment head on text layer 14, but model only has 4 text layers") and the app aborts in
* whisper_free_state. Measured on an M5 Pro, Electron 42, large-v3-turbo, 2.7 s and 21 s clips:
- * the shipped binary crashed in 4 of 4 runs outside the app and took 7-10 s per dictation inside
- * it; with the params initialized it took 0.56 s and 0.93 s, no crash. The fix starts from
+ * the shipped binary crashed in 4 of 4 runs outside the app; with the params initialized it ran
+ * without a crash (0.56 s and 0.93 s on Metal). The slow dictation seen inside the packaged app is
+ * a separate bug (Metal cannot read its shaders inside app.asar). The fix starts from
* whisper_context_default_params(), exactly what whisper.cpp's own examples do.
*
* GUARD: src/core/speech/smart-whisper-patch.test.ts asserts both markers are present in the