Streaming zamiany tekstu na mowę

import os
import uuid
from dotenv import load_dotenv
from elevenlabs import VoiceSettings
from elevenlabs.client import ElevenLabs
load_dotenv()
ELEVENLABS_API_KEY = os.getenv("ELEVENLABS_API_KEY")
elevenlabs = ElevenLabs(
    api_key=ELEVENLABS_API_KEY,
)
def text_to_speech_file(text: str) -> str:
    # Calling the text_to_speech conversion API with detailed parameters
    response = elevenlabs.text_to_speech.convert(
        voice_id="pNInz6obpgDQGcFmaJgB", # Adam pre-made voice
        output_format="mp3_22050_32",
        text=text,
        model_id="eleven_flash_v2_5", # use the flash model for low latency
        # Optional voice settings that allow you to customize the output
        voice_settings=VoiceSettings(
            stability=0.0,
            similarity_boost=1.0,
            style=0.0,
            use_speaker_boost=True,
            speed=1.0,
        ),
    )
    # uncomment the line below to play the audio back
    # play(response)
    # Generating a unique file name for the output MP3 file
    save_file_path = f"{uuid.uuid4()}.mp3"
    # Writing the audio to a file
    with open(save_file_path, "wb") as f:
        for chunk in response:
            if chunk:
                f.write(chunk)
    print(f"{save_file_path}: A new audio file was saved successfully!")
    # Return the path of the saved audio file
    return save_file_path

text_to_speech_file("Hello World")

import os
from typing import IO
from io import BytesIO
from dotenv import load_dotenv
from elevenlabs import VoiceSettings
from elevenlabs.client import ElevenLabs
load_dotenv()
ELEVENLABS_API_KEY = os.getenv("ELEVENLABS_API_KEY")
elevenlabs = ElevenLabs(
    api_key=ELEVENLABS_API_KEY,
)
def text_to_speech_stream(text: str) -> IO[bytes]:
    # Perform the text-to-speech conversion
    response = elevenlabs.text_to_speech.stream(
        voice_id="pNInz6obpgDQGcFmaJgB", # Adam pre-made voice
        output_format="mp3_22050_32",
        text=text,
        model_id="eleven_multilingual_v2",
        # Optional voice settings that allow you to customize the output
        voice_settings=VoiceSettings(
            stability=0.0,
            similarity_boost=1.0,
            style=0.0,
            use_speaker_boost=True,
            speed=1.0,
        ),
    )
    # Create a BytesIO object to hold the audio data in memory
    audio_stream = BytesIO()
    # Write each chunk of audio data to the stream
    for chunk in response:
        if chunk:
            audio_stream.write(chunk)
    # Reset stream position to the beginning
    audio_stream.seek(0)
    # Return the stream for further use
    return audio_stream

text_to_speech_stream("This is James")