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.
25 lines
833 B
Python
25 lines
833 B
Python
import speech_recognition as sr
|
|
|
|
r = sr.Recognizer()
|
|
m = sr.Microphone()
|
|
|
|
try:
|
|
print("A moment of silence, please...")
|
|
with m as source: r.adjust_for_ambient_noise(source)
|
|
print("Set minimum energy threshold to {}".format(r.energy_threshold))
|
|
while True:
|
|
print("Say something!")
|
|
with m as source: audio = r.listen(source)
|
|
print("Got it! Now to recognize it...")
|
|
try:
|
|
# recognize speech using Google Speech Recognition
|
|
value = r.recognize_google(audio)
|
|
|
|
print("You said {}".format(value))
|
|
except sr.UnknownValueError:
|
|
print("Oops! Didn't catch that")
|
|
except sr.RequestError as e:
|
|
print("Uh oh! Couldn't request results from Google Speech Recognition service; {0}".format(e))
|
|
except KeyboardInterrupt:
|
|
pass
|