From d5a940ea7898c4a4f93419183c80ed5a815e5945 Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Tue, 25 Aug 2026 17:06:21 +0000
Subject: [PATCH] docs(openrouter-stt): document 50 MiB transcription request
 body cap

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 skills/openrouter-stt/SKILL.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/skills/openrouter-stt/SKILL.md b/skills/openrouter-stt/SKILL.md
index 08444a0..cf9dd4d 100644
--- a/skills/openrouter-stt/SKILL.md
+++ b/skills/openrouter-stt/SKILL.md
@@ -192,7 +192,7 @@ print(res.json()["text"])
 
 **400 with a `ZodError`** — a required field is missing or the wrong type. The body looks like `{"success":false,"error":{"name":"ZodError","message":"[...]"}}` — the nested `message` JSON string names the bad path (commonly `input_audio.data` or `input_audio.format`).
 
-**413 / request too large** — base64 inflates bytes by ~33%, so a large raw file becomes an even larger JSON payload. Use a smaller source file (compressed format, lower sample rate, or trimmed clip).
+**413 / request too large** — the JSON request body is capped at 50 MiB, checked against `Content-Length` at the edge, so an oversized request is rejected before any audio is read. Base64 inflates bytes by ~33%, so plan for a raw file of roughly 37 MB or less. Use a smaller source file (compressed format, lower sample rate, or trimmed clip).
 
 **Model not found** — use the full slug from `/api/v1/models?output_modalities=transcription` (`google/chirp-3`, not `chirp-3`).