SRT to voice

[0-666]

I have an SRT file with n number of segments and I want to generate TTS of each segments separately and save it as 1.wav 2.wav to n.wav how can I call alltalktts api.

[erew123]

Something like this:

srttotts.py

import requests
import os
import re
import sys

# Try importing pysrt; install it if missing
try:
    import pysrt
except ImportError:
    print("pysrt not found. Installing it now...")
    os.system(f"{sys.executable} -m pip install pysrt")
    import pysrt

# Configuration for TTS API
API_URL = "http://127.0.0.1:7851/api/tts-generate"  # Replace with actual IP and port
CHARACTER_VOICE = "female_01.wav"  # Replace with the desired character voice file
LANGUAGE = "en"  # Replace with the desired language

def parse_srt(file_path):
    """Parse an SRT file and return a list of subtitle texts."""
    subs = pysrt.open(file_path)
    return [sub.text for sub in subs]

def sanitize_filename(filename):
    """Sanitize filename to remove special characters, spaces, and extensions."""
    # Remove all non-alphanumeric characters except underscores
    sanitized = re.sub(r'[^A-Za-z0-9_]', '', filename)
    return sanitized

def generate_tts(segment, output_file):
    """Send a TTS generation request to the API."""
    payload = {
        "text_input": segment,
        "text_filtering": "standard",
        "character_voice_gen": CHARACTER_VOICE,
        "narrator_enabled": "false",  # Change to "true" if narrator is used
        "narrator_voice_gen": "male_01.wav",
        "text_not_inside": "character",
        "language": LANGUAGE,
        "output_file_name": output_file,
        "output_file_timestamp": "false",
        "autoplay": "false",
    }

    response = requests.post(API_URL, data=payload)
    if response.status_code == 200:
        result = response.json()
        if result["status"] == "generate-success":
            print(f"TTS generated for segment: {output_file}.wav")
        else:
            print(f"Failed to generate TTS for {output_file}.wav: {result}")
    else:
        print(f"API Error {response.status_code}: {response.text}")

def process_srt_to_tts(srt_path):
    """Process the SRT file and generate TTS files."""
    # Parse the SRT file
    segments = parse_srt(srt_path)

    # Extract the base name of the SRT file without extension
    base_name = os.path.splitext(os.path.basename(srt_path))[0]
    sanitized_base_name = sanitize_filename(base_name)
    
    # Generate TTS for each segment
    for i, segment in enumerate(segments, start=1):
        # Create output file name with SRT base name as prefix
        output_file = f"{sanitized_base_name}_{i:06d}"  # Format as 'myfile_000001', 'myfile_000002', etc.
        generate_tts(segment, output_file)

if __name__ == "__main__":
    # Check if the script is called with a command-line argument
    if len(sys.argv) < 2:
        print("Usage: python script.py <path_to_srt_file>")
        sys.exit(1)
    
    # Get the SRT file path from the command-line arguments
    SRT_FILE_PATH = sys.argv[1]
    
    # Check if the file exists
    if not os.path.exists(SRT_FILE_PATH):
        print(f"Error: File '{SRT_FILE_PATH}' not found.")
        sys.exit(1)

    # Process the SRT file
    process_srt_to_tts(SRT_FILE_PATH)

[0-666]

Yes sir 😀 that what's I need ,thankyou.

…

On Tue, Nov 19, 2024, 9:36 PM erew123 ***@***.***> wrote: Something like this: image.png (view on web) <https://github.com/user-attachments/assets/1eae3323-4e16-4d6f-80df-b335dd640baa> srttotts.py import requests import os import re import sys # Try importing pysrt; install it if missing try: import pysrt except ImportError: print("pysrt not found. Installing it now...") os.system(f"{sys.executable} -m pip install pysrt") import pysrt # Configuration for TTS API API_URL = "http://127.0.0.1:7851/api/tts-generate" # Replace with actual IP and port CHARACTER_VOICE = "female_01.wav" # Replace with the desired character voice file LANGUAGE = "en" # Replace with the desired language def parse_srt(file_path): """Parse an SRT file and return a list of subtitle texts.""" subs = pysrt.open(file_path) return [sub.text for sub in subs] def sanitize_filename(filename): """Sanitize filename to remove special characters, spaces, and extensions.""" # Remove all non-alphanumeric characters except underscores sanitized = re.sub(r'[^A-Za-z0-9_]', '', filename) return sanitized def generate_tts(segment, output_file): """Send a TTS generation request to the API.""" payload = { "text_input": segment, "text_filtering": "standard", "character_voice_gen": CHARACTER_VOICE, "narrator_enabled": "false", # Change to "true" if narrator is used "narrator_voice_gen": "male_01.wav", "text_not_inside": "character", "language": LANGUAGE, "output_file_name": output_file, "output_file_timestamp": "false", "autoplay": "false", } response = requests.post(API_URL, data=payload) if response.status_code == 200: result = response.json() if result["status"] == "generate-success": print(f"TTS generated for segment: {output_file}.wav") else: print(f"Failed to generate TTS for {output_file}.wav: {result}") else: print(f"API Error {response.status_code}: {response.text}") def process_srt_to_tts(srt_path): """Process the SRT file and generate TTS files.""" # Parse the SRT file segments = parse_srt(srt_path) # Extract the base name of the SRT file without extension base_name = os.path.splitext(os.path.basename(srt_path))[0] sanitized_base_name = sanitize_filename(base_name) # Generate TTS for each segment for i, segment in enumerate(segments, start=1): # Create output file name with SRT base name as prefix output_file = f"{sanitized_base_name}_{i:06d}" # Format as 'myfile_000001', 'myfile_000002', etc. generate_tts(segment, output_file) if __name__ == "__main__": # Check if the script is called with a command-line argument if len(sys.argv) < 2: print("Usage: python script.py <path_to_srt_file>") sys.exit(1) # Get the SRT file path from the command-line arguments SRT_FILE_PATH = sys.argv[1] # Check if the file exists if not os.path.exists(SRT_FILE_PATH): print(f"Error: File '{SRT_FILE_PATH}' not found.") sys.exit(1) # Process the SRT file process_srt_to_tts(SRT_FILE_PATH) — Reply to this email directly, view it on GitHub <#412 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AYOWA4SONJFEOGSLBC4MB5T2BNOXHAVCNFSM6AAAAABSCNCNOOVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCMZQG44DEOA> . You are receiving this because you authored the thread.Message ID: ***@***.***>

[subof]

I would like to see this section in the web-UI for dubbing subtitles, if possible.
And it would be nice to be able to clone speaker voices right акщь the track and assign them from existing samples and models.
THank you