marcocosta10000/PsAgentAI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(voice): transcribe Telegram voice notes with SpeechRecognition

Browse Source 
Add a voice message handler that downloads OGG audio, converts it to
WAV via pydub/ffmpeg, and transcribes it with Google Speech Recognition
(pt-BR) before feeding the text into the normal message pipeline.

Also extract shared text processing into process_text_message, guard
against updates without a text attribute, switch the default AI provider
to openrouter with deepseek-v4-flash, and document the ffmpeg system
requirement in DEPLOY.md.
This commit is contained in:
marcocosta10000
2026-10-25 17:27:42 -03:00
parent 6b3b6541a7
commit 25288d2c0f
73 changed files with 139973 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env
+2 -2
View File
@@ -5,10 +5,10 @@ TELEGRAM_CHAT_ID=7889499475
# AI Provider (openrouter | stepfun | qwencloud | llamacpp)
AI_PROVIDER=stepfun
AI_PROVIDER=openrouter
# Default AI Model
DEFAULT_MODEL=step-3.7-flash
DEFAULT_MODEL=deepseek/deepseek-v4-flash-0731