From afa73ef882db686e39604a4d4157b856f4ead46f Mon Sep 17 00:00:00 2001
From: Vance Ingalls <vance@heygen.com>
Date: Wed, 25 Mar 2026 16:53:18 -0700
Subject: [PATCH] fix(cli): use --output-json-full for word-level timestamps

--output-json only produces segment-level timing (no tokens).
--output-json-full is required for word-level timestamps that
the captions template needs. Special tokens are filtered out
by the patchTranscript function.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 packages/cli/src/whisper/transcribe.ts | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/packages/cli/src/whisper/transcribe.ts b/packages/cli/src/whisper/transcribe.ts
index fbebb55f0c..792074a58c 100644
--- a/packages/cli/src/whisper/transcribe.ts
+++ b/packages/cli/src/whisper/transcribe.ts
@@ -102,7 +102,17 @@ export async function transcribe(
 
   execFileSync(
     whisper.executablePath,
-    ["--model", modelPath, "--output-json", "--output-file", outputBase, "--dtw", model, wavPath],
+    [
+      "--model",
+      modelPath,
+      "--output-json-full",
+      "--output-file",
+      outputBase,
+      "--dtw",
+      model,
+      "--suppress-nst",
+      wavPath,
+    ],
     { stdio: "ignore", timeout: 300_000 },
   );