recognize_ibm()

recognize_ibm(
    audio_data: AudioData,
    key: str,
    language: str = "en-US",
    show_all: bool = False
) -> str | tuple[str, float] | dict

import speech_recognition as sr

# Initialize recognizer
r = sr.Recognizer()

# Your IBM Watson API key
IBM_KEY = "your-ibm-api-key"

# Record audio
with sr.Microphone() as source:
    print("Say something!")
    audio = r.listen(source)

# Recognize with IBM Watson
try:
    text, confidence = r.recognize_ibm(audio, key=IBM_KEY)
    print(f"You said: {text}")
    print(f"Confidence: {confidence:.2%}")
except sr.UnknownValueError:
    print("Could not understand audio")
except sr.RequestError as e:
    print(f"API error: {e}")

import speech_recognition as sr

IBM_KEY = "your-api-key"

r = sr.Recognizer()

# Spanish recognition
with sr.Microphone() as source:
    print("Diga algo...")
    audio = r.listen(source)

try:
    text, confidence = r.recognize_ibm(
        audio,
        key=IBM_KEY,
        language="es-ES"
    )
    print(f"Usted dijo: {text}")
    print(f"Confianza: {confidence:.2%}")
except sr.UnknownValueError:
    print("No se pudo entender el audio")

import speech_recognition as sr
import json

IBM_KEY = "your-api-key"

r = sr.Recognizer()

with sr.Microphone() as source:
    audio = r.listen(source)

try:
    # Get complete response
    response = r.recognize_ibm(
        audio,
        key=IBM_KEY,
        show_all=True
    )
    
    print(json.dumps(response, indent=2))
    
    # Access multiple alternatives
    for result in response.get('results', []):
        for alternative in result.get('alternatives', []):
            print(f"Transcript: {alternative['transcript']}")
            if 'confidence' in alternative:
                print(f"Confidence: {alternative['confidence']:.2%}")
except sr.UnknownValueError:
    print("Could not understand audio")

import speech_recognition as sr

IBM_KEY = "your-api-key"

r = sr.Recognizer()

# Load audio file
with sr.AudioFile("speech.wav") as source:
    audio = r.record(source)

try:
    text, confidence = r.recognize_ibm(audio, key=IBM_KEY)
    print(f"Transcript: {text}")
    print(f"Confidence: {confidence:.2%}")
except sr.RequestError as e:
    print(f"Error: {e}")

import speech_recognition as sr
import os

# Store API key in environment variable
IBM_KEY = os.getenv("IBM_WATSON_API_KEY")

r = sr.Recognizer()

with sr.Microphone() as source:
    audio = r.listen(source)

try:
    text, confidence = r.recognize_ibm(audio, key=IBM_KEY)
    print(f"Transcript: {text}")
except sr.RequestError as e:
    print(f"Error: {e}")

import speech_recognition as sr

IBM_KEY = "your-api-key"

r = sr.Recognizer()

with sr.Microphone() as source:
    print("请说话...")
    audio = r.listen(source)

try:
    text, confidence = r.recognize_ibm(
        audio,
        key=IBM_KEY,
        language="zh-CN"
    )
    print(f"你说: {text}")
except sr.UnknownValueError:
    print("无法理解音频")

import speech_recognition as sr

IBM_KEY = "your-api-key-here"

r = sr.Recognizer()

with sr.Microphone() as source:
    audio = r.listen(source)

text, confidence = r.recognize_ibm(audio, key=IBM_KEY)
print(text)