Real-time Voice Streaming

from fish_audio_sdk import WebSocketSession, TTSRequest

# Initialize WebSocket session
session = WebSocketSession("your_api_key")

# Stream text word by word
def stream_text():
    text = "Hello, this is being generated in real time"
    for word in text.split():
        yield word + " "

# Generate speech as text streams
request = TTSRequest(
    text="",
    reference_id="your_voice_model_id",
    temperature=0.7,  # Controls variation
    top_p=0.7  # Controls diversity
)

with open("output.mp3", "wb") as f:
    for audio_chunk in session.tts(request, stream_text()):
        f.write(audio_chunk)

request = TTSRequest(
    text="",
    reference_id="model_id",
    latency="balanced"  # For faster response
)

def chatbot_response(user_input):
    # Get AI response (streaming)
    ai_text = get_ai_response(user_input)
    
    # Convert to speech in real-time
    for text_chunk in ai_text:
        for audio_chunk in session.tts(request, text_chunk):
            play_audio(audio_chunk)

def live_translate(source_audio):
    # Transcribe source audio
    text = transcribe(source_audio)
    
    # Translate text
    translated = translate(text, target_language)
    
    # Stream translated speech
    for chunk in stream_text(translated):
        generate_speech(chunk)

def interactive_story():
    story_parts = [
        "Once upon a time,",
        "in a land far away,",
        "there lived a brave knight..."
    ]
    
    for part in story_parts:
        # Generate and play each part
        stream_speech(part)
        # Wait for user input
        user_choice = get_user_input()
        # Continue based on choice

def virtual_assistant():
    while True:
        # Listen for wake word
        if detect_wake_word():
            # Start streaming response
            response = process_command()
            stream_speech(response)

def live_commentary(event_stream):
    for event in event_stream:
        # Generate commentary
        commentary = generate_commentary(event)
        # Stream immediately
        stream_speech(commentary)

# Start with one voice
request1 = TTSRequest(reference_id="voice1")
stream_speech("Hello from voice one.", request1)

# Switch to another
request2 = TTSRequest(reference_id="voice2")
stream_speech("And now voice two!", request2)

def emotional_speech(text, emotion):
    emotional_text = f"({emotion}) {text}"
    stream_speech(emotional_text)

request = TTSRequest(
    text="",
    prosody={
        "speed": 1.5,  # 1.5x speed
        "volume": 0    # Normal volume
    }
)