IBM Watson Speech to Text

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

IBM_API_KEY = "your_ibm_watson_api_key"

r = sr.Recognizer()

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

try:
    text, confidence = r.recognize_ibm(audio, key=IBM_API_KEY)
    print(f"Transcription: {text}")
    print(f"Confidence: {confidence:.2%}")
except sr.UnknownValueError:
    print("IBM Watson could not understand audio")
except sr.RequestError as e:
    print(f"Could not request results; {e}")

import speech_recognition as sr

IBM_API_KEY = "your_ibm_watson_api_key"

r = sr.Recognizer()

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

print("Transcribing...")
try:
    text, confidence = r.recognize_ibm(audio, key=IBM_API_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"Error: {e}")

import speech_recognition as sr
import json

IBM_API_KEY = "your_api_key"

r = sr.Recognizer()

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

# Get full response
response = r.recognize_ibm(
    audio,
    key=IBM_API_KEY,
    show_all=True
)

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

# Access detailed results
for result in response.get("results", []):
    for alternative in result.get("alternatives", []):
        print(f"Transcript: {alternative['transcript']}")
        print(f"Confidence: {alternative['confidence']:.2%}")

import speech_recognition as sr
import os

IBM_API_KEY = os.environ.get("IBM_WATSON_API_KEY")

if not IBM_API_KEY:
    raise ValueError("IBM_WATSON_API_KEY environment variable not set")

r = sr.Recognizer()

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

text, confidence = r.recognize_ibm(audio, key=IBM_API_KEY)
print(f"{text} ({confidence:.0%} confidence)")

import speech_recognition as sr

IBM_API_KEY = "your_api_key"

r = sr.Recognizer()

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

try:
    text, confidence = r.recognize_ibm(
        audio,
        key=IBM_API_KEY,
        language="en-US"
    )
    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 "unauthorized" in error_msg or "401" in error_msg:
        print("Invalid API key")
    elif "forbidden" in error_msg or "403" in error_msg:
        print("Access forbidden - check your subscription")
    elif "connection" in error_msg:
        print("Network connection error")
    else:
        print(f"API error: {e}")

import speech_recognition as sr

IBM_API_KEY = "your_api_key"

r = sr.Recognizer()
r.operation_timeout = 15  # Wait up to 15 seconds

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

try:
    text, _ = r.recognize_ibm(audio, key=IBM_API_KEY)
    print(text)
except sr.WaitTimeoutError:
    print("Request timed out")

from ibm_watson import SpeechToTextV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator

authenticator = IAMAuthenticator('your_api_key')
speech_to_text = SpeechToTextV1(authenticator=authenticator)

with open('audio.wav', 'rb') as audio_file:
    response = speech_to_text.recognize(
        audio=audio_file,
        content_type='audio/wav',
        speaker_labels=True  # Enable speaker diarization
    ).get_result()

for result in response['results']:
    for alternative in result['alternatives']:
        print(alternative['transcript'])

for speaker in response['speaker_labels']:
    print(f"Speaker {speaker['speaker']}: {speaker['from']}s - {speaker['to']}s")

from ibm_watson import SpeechToTextV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator

authenticator = IAMAuthenticator('your_api_key')
speech_to_text = SpeechToTextV1(authenticator=authenticator)

with open('audio.wav', 'rb') as audio_file:
    response = speech_to_text.recognize(
        audio=audio_file,
        content_type='audio/wav',
        language_customization_id='your-custom-model-id'
    ).get_result()

from ibm_watson import SpeechToTextV1
from ibm_cloud_sdk_core.authenticators import IAMAuthenticator

authenticator = IAMAuthenticator('your_api_key')
speech_to_text = SpeechToTextV1(authenticator=authenticator)

with open('audio.wav', 'rb') as audio_file:
    response = speech_to_text.recognize(
        audio=audio_file,
        content_type='audio/wav',
        smart_formatting=True  # Format dates, times, numbers, etc.
    ).get_result()