common/hermes
2
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

add .aac audio file format support to transcription tool (#3865)

Browse Source 
Co-authored-by: Adrian Scott <adrian@adrianscott.com>
This commit is contained in:
Teknium
2026-03-29 21:27:03 -07:00
committed by GitHub
parent f39ca81bab
commit 2ff2cd3a59
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tools/transcription_tools.py
View File

@@ -12,7 +12,7 @@ Provides speech-to-text transcription with three providers:
Used by the messaging gateway to automatically transcribe voice messages Used by the messaging gateway to automatically transcribe voice messages
sent by users on Telegram, Discord, WhatsApp, Slack, and Signal. 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:: 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") 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") 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"} LOCAL_NATIVE_AUDIO_FORMATS = {".wav", ".aiff", ".aif"}
MAX_FILE_SIZE = 25 * 1024 * 1024 # 25 MB MAX_FILE_SIZE = 25 * 1024 * 1024 # 25 MB