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.
23 lines
273 B
Python
23 lines
273 B
Python
class SetupError(Exception):
|
|
pass
|
|
|
|
|
|
class WaitTimeoutError(Exception):
|
|
pass
|
|
|
|
|
|
class RequestError(Exception):
|
|
pass
|
|
|
|
|
|
class UnknownValueError(Exception):
|
|
pass
|
|
|
|
|
|
class TranscriptionNotReady(Exception):
|
|
pass
|
|
|
|
|
|
class TranscriptionFailed(Exception):
|
|
pass
|