Wit.ai Speech Recognition

recognize_wit(
    audio_data: AudioData,
    key: str,
    show_all: bool = False
) -> str | dict

import speech_recognition as sr

WIT_AI_KEY = "YOUR_WIT_AI_API_KEY"

r = sr.Recognizer()

with sr.AudioFile("audio.wav") as source:
    audio = r.record(source)

try:
    text = r.recognize_wit(audio, key=WIT_AI_KEY)
    print(f"Wit.ai thinks you said: {text}")
except sr.UnknownValueError:
    print("Wit.ai could not understand audio")
except sr.RequestError as e:
    print(f"Could not request results from Wit.ai; {e}")

import speech_recognition as sr

WIT_AI_KEY = "YOUR_WIT_AI_API_KEY"

r = sr.Recognizer()

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

print("Recognizing...")
try:
    text = r.recognize_wit(audio, key=WIT_AI_KEY)
    print(f"You said: {text}")
except sr.UnknownValueError:
    print("Could not understand audio")
except sr.RequestError as e:
    print(f"Error: {e}")

import speech_recognition as sr
import json

WIT_AI_KEY = "YOUR_WIT_AI_API_KEY"

r = sr.Recognizer()

with sr.AudioFile("audio.wav") as source:
    audio = r.record(source)

# Get full response
response = r.recognize_wit(audio, key=WIT_AI_KEY, show_all=True)

print(json.dumps(response, indent=2))

# Access specific fields
if "_text" in response:
    print(f"Transcription: {response['_text']}")

if "intents" in response:
    for intent in response["intents"]:
        print(f"Intent: {intent['name']} (confidence: {intent['confidence']})")

if "entities" in response:
    print(f"Entities: {response['entities']}")

import speech_recognition as sr
import os

WIT_AI_KEY = os.environ.get("WIT_AI_KEY")

if not WIT_AI_KEY:
    raise ValueError("WIT_AI_KEY environment variable not set")

r = sr.Recognizer()

with sr.AudioFile("audio.wav") as source:
    audio = r.record(source)

text = r.recognize_wit(audio, key=WIT_AI_KEY)
print(text)

import speech_recognition as sr

WIT_AI_KEY = "YOUR_WIT_AI_API_KEY"

r = sr.Recognizer()

with sr.AudioFile("audio.wav") as source:
    audio = r.record(source)

try:
    text = r.recognize_wit(audio, key=WIT_AI_KEY)
    print(f"Transcription: {text}")
    
except sr.UnknownValueError:
    # Speech was unintelligible
    print("Could not understand the audio")
    
except sr.RequestError as e:
    # API request failed
    error_msg = str(e).lower()
    if "invalid" in error_msg or "key" in error_msg:
        print("Invalid API key")
    elif "connection" in error_msg:
        print("Network connection error")
    elif "rate" in error_msg or "limit" in error_msg:
        print("Rate limit exceeded")
    else:
        print(f"API error: {e}")

import speech_recognition as sr

WIT_AI_KEY = "YOUR_WIT_AI_API_KEY"

r = sr.Recognizer()
r.operation_timeout = 10  # Wait up to 10 seconds

with sr.AudioFile("audio.wav") as source:
    audio = r.record(source)

try:
    text = r.recognize_wit(audio, key=WIT_AI_KEY)
    print(text)
except sr.WaitTimeoutError:
    print("Request timed out")

import speech_recognition as sr

# Different apps for different languages
WIT_EN_KEY = "english_app_key"
WIT_ES_KEY = "spanish_app_key"
WIT_FR_KEY = "french_app_key"

r = sr.Recognizer()

with sr.AudioFile("audio.wav") as source:
    audio = r.record(source)

# Detect language first (or let user choose)
language = "english"  # This would come from language detection

if language == "english":
    text = r.recognize_wit(audio, key=WIT_EN_KEY)
elif language == "spanish":
    text = r.recognize_wit(audio, key=WIT_ES_KEY)
elif language == "french":
    text = r.recognize_wit(audio, key=WIT_FR_KEY)

print(text)

import speech_recognition as sr

WIT_AI_KEY = "YOUR_WIT_AI_API_KEY"

r = sr.Recognizer()

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

try:
    # Get full response with intents
    response = r.recognize_wit(audio, key=WIT_AI_KEY, show_all=True)
    
    text = response.get("_text", "")
    print(f"You said: {text}")
    
    # Process intents
    intents = response.get("intents", [])
    if intents:
        primary_intent = intents[0]
        intent_name = primary_intent.get("name")
        confidence = primary_intent.get("confidence", 0)
        
        if confidence > 0.7:
            if intent_name == "turn_on_light":
                print("Turning on the light...")
            elif intent_name == "play_music":
                print("Playing music...")
            elif intent_name == "weather":
                print("Checking weather...")
        else:
            print("Intent confidence too low")
    else:
        print("No intent detected")
        
except sr.UnknownValueError:
    print("Could not understand audio")
except sr.RequestError as e:
    print(f"Error: {e}")

import speech_recognition as sr
import time

WIT_AI_KEY = "YOUR_WIT_AI_API_KEY"

def recognize_with_retry(audio, max_retries=3):
    r = sr.Recognizer()
    
    for attempt in range(max_retries):
        try:
            return r.recognize_wit(audio, key=WIT_AI_KEY)
        except sr.RequestError as e:
            if "rate" in str(e).lower() and attempt < max_retries - 1:
                wait_time = 2 ** attempt  # Exponential backoff
                print(f"Rate limited. Waiting {wait_time} seconds...")
                time.sleep(wait_time)
            else:
                raise
    
    raise sr.RequestError("Max retries exceeded")

# Use it
with sr.AudioFile("audio.wav") as source:
    audio = r.record(source)

text = recognize_with_retry(audio)
print(text)