audiolib.py

import wave
import pyaudio
from ailib import whisper_transcribe
##################################################
# Configuración del audio
FORMAT = pyaudio.paInt16
CHANNELS = 1
RATE = 16000
CHUNK = 1024
##################################################
def wavsave(frames, fn):
    wf = wave.open(fn, 'wb')
    wf.setnchannels(CHANNELS)
    wf.setsampwidth(2)  #audio.get_sample_size(FORMAT))
    wf.setframerate(RATE)
    wf.writeframes(b''.join(frames))
    wf.close()

def grabar_audio():
    audio = pyaudio.PyAudio()
    stream = audio.open(format=FORMAT, channels=CHANNELS, rate=RATE, input=True, frames_per_buffer=CHUNK)
    frames = []
    while True:
        data = stream.read(CHUNK)
        frames.append(data)
        if len(frames) >= 50:  # Grabar durante 5 segundos
            break
    stream.stop_stream()
    stream.close()
    audio.terminate()
    return frames

def transcribir_audio(frames):
    wavsave(frames, 'temp.wav')
    return whisper_transcribe('temp.wav')