marcocosta10000
25288d2c0f
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.
10 lines
169 B
Plaintext
Executable File
10 lines
169 B
Plaintext
Executable File
python-dotenv==1.0.1
|
|
requests==2.32.3
|
|
python-telegram-bot==20.7
|
|
openai==1.12.0
|
|
PyMuPDF==1.28.0
|
|
python-docx==1.2.0
|
|
Pillow==12.2.0
|
|
SpeechRecognition==3.10.0
|
|
pydub==0.25.1
|