speechrecognition

import speech_recognition as sr import os r = sr.Recognizer() # --- Option 1: Listen from Microphone (requires PyAudio and PortAudio) --- try: import pyaudio with sr.Microphone() as source: print("Say something into the microphone!") r.adjust_for_ambient_noise(source, duration=1) # Adjust for ambient noise audio = r.listen(source, timeout=5, phrase_time_limit=10) print("Processing microphone input...") text = r.recognize_google(audio) print(f"You said (Google Web Speech): {text}") except sr.WaitTimeoutError: print("No speech detected within the timeout period for microphone.") except sr.UnknownValueError: print("Google Web Speech Recognition could not understand microphone audio.") except sr.RequestError as e: print(f"Could not request results from Google Web Speech service for microphone; {e}") except ImportError: print("PyAudio not installed. Cannot use microphone. To enable, install with: pip install pyaudio") except Exception as e: print(f"An unexpected error occurred with microphone input: {e}") # --- Option 2: Transcribe an Audio File (e.g., using Google Web Speech API) --- file_path = "dummy_audio.wav" # Create a dummy WAV file for demonstration if it doesn't exist if not os.path.exists(file_path): try: from pydub import AudioSegment AudioSegment.silent(duration=1000, frame_rate=16000).export(file_path, format="wav") print(f"\nCreated a dummy WAV file: {file_path}") except ImportError: print("\npydub not installed, cannot create dummy audio. Please provide a WAV file manually.") print("Skipping audio file transcription example.") file_path = None if file_path: try: with sr.AudioFile(file_path) as source: audio = r.record(source) # Read the entire audio file print(f"Transcribing '{file_path}'...") text = r.recognize_google(audio) print(f"Transcription (Google Web Speech): {text}") except sr.UnknownValueError: print(f"Google Web Speech Recognition could not understand audio from '{file_path}'.") except sr.RequestError as e: print(f"Could not request results from Google Web Speech service for '{file_path}'; {e}") except Exception as e: print(f"An error occurred with audio file transcription: {e}") # --- Option 3: Using a Commercial API (e.g., OpenAI Whisper API) --- # Requires 'pip install openai' and setting OPENAI_API_KEY environment variable OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "") if OPENAI_API_KEY and file_path: print("\nAttempting transcription with OpenAI Whisper API...") try: with sr.AudioFile(file_path) as source: audio = r.record(source) text = r.recognize_whisper_api(audio, api_key=OPENAI_API_KEY) print(f"Transcription (OpenAI Whisper API): {text}") except sr.UnknownValueError: print(f"OpenAI Whisper API could not understand audio from '{file_path}'.") except sr.RequestError as e: print(f"Could not request results from OpenAI Whisper API service; {e}") except Exception as e: print(f"An error occurred with OpenAI Whisper API: {e}") else: print("\nSkipping OpenAI Whisper API example (OPENAI_API_KEY not set or no audio file for transcription).")