google-cloud-speech

import os from google.cloud import speech # Set the path to your service account key file # This is typically done via the GOOGLE_APPLICATION_CREDENTIALS environment variable. # For local testing, you might set it in code (not recommended for production). # os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "/path/to/your/keyfile.json" def transcribe_audio(audio_file_path): client = speech.SpeechClient() with open(audio_file_path, "rb") as audio_file: content = audio_file.read() audio = speech.RecognitionAudio(content=content) config = speech.RecognitionConfig( encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16, sample_rate_hertz=16000, language_code="en-US", ) try: response = client.recognize(config=config, audio=audio) for result in response.results: print(f"Transcript: {result.alternatives[0].transcript}") except Exception as e: print(f"An error occurred: {e}") # Example usage (replace with your actual audio file) if __name__ == "__main__": # Make sure you have an audio file named 'audio.wav' (16-bit, 16000 Hz, mono WAV) # and that GOOGLE_APPLICATION_CREDENTIALS is set up. # For testing, create a dummy WAV file or use a real one. # e.g., using `scipy.io.wavfile.write('audio.wav', 16000, np.zeros(16000, dtype=np.int16))` # Or, for a real test, ensure you have a small audio.wav file. # You must have a service account key file and set the GOOGLE_APPLICATION_CREDENTIALS # environment variable pointing to it, or pass credentials explicitly. # e.g., export GOOGLE_APPLICATION_CREDENTIALS="/path/to/your/keyfile.json" # This example assumes a 'test.wav' file exists in the same directory # and is a LINEAR16 (16-bit PCM), 16000 Hz, mono WAV file. # Create a dummy file for demonstration if needed: # import numpy as np # from scipy.io.wavfile import write as write_wav # write_wav('test.wav', 16000, np.zeros(16000, dtype=np.int16)) # Placeholder for a real audio file path # In a real scenario, ensure this file exists and is correctly formatted. # For this quickstart, you might use a short, simple WAV file. audio_test_file = "test.wav" print(f"Attempting to transcribe: {audio_test_file}") print("Ensure GOOGLE_APPLICATION_CREDENTIALS is set and the file exists and is LINEAR16, 16000 Hz, mono.") transcribe_audio(audio_test_file)