From 2ff2cd3a59bf27a51f7e474dfe3707f32e12e984 Mon Sep 17 00:00:00 2001 From: Teknium <127238744+teknium1@users.noreply.github.com> Date: Sun, 29 Mar 2026 21:27:03 -0700 Subject: [PATCH] add .aac audio file format support to transcription tool (#3865) Co-authored-by: Adrian Scott --- tools/transcription_tools.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/transcription_tools.py b/tools/transcription_tools.py index 0c0a1fc9f..70791b0ca 100644 --- a/tools/transcription_tools.py +++ b/tools/transcription_tools.py @@ -12,7 +12,7 @@ Provides speech-to-text transcription with three providers: Used by the messaging gateway to automatically transcribe voice messages sent by users on Telegram, Discord, WhatsApp, Slack, and Signal. -Supported input formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg +Supported input formats: mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg, aac Usage:: @@ -60,7 +60,7 @@ COMMON_LOCAL_BIN_DIRS = ("/opt/homebrew/bin", "/usr/local/bin") GROQ_BASE_URL = os.getenv("GROQ_BASE_URL", "https://api.groq.com/openai/v1") OPENAI_BASE_URL = os.getenv("STT_OPENAI_BASE_URL", "https://api.openai.com/v1") -SUPPORTED_FORMATS = {".mp3", ".mp4", ".mpeg", ".mpga", ".m4a", ".wav", ".webm", ".ogg"} +SUPPORTED_FORMATS = {".mp3", ".mp4", ".mpeg", ".mpga", ".m4a", ".wav", ".webm", ".ogg", ".aac"} LOCAL_NATIVE_AUDIO_FORMATS = {".wav", ".aiff", ".aif"} MAX_FILE_SIZE = 25 * 1024 * 1024 # 25 MB