File size: 2,398 Bytes
e15bf7c ce21c3a e15bf7c ce21c3a e15bf7c ce21c3a e15bf7c ce21c3a e15bf7c ce21c3a e15bf7c ce21c3a e15bf7c ce21c3a e15bf7c ce21c3a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 | import streamlit as st
from pydub import AudioSegment
import tempfile
import os
def merge_audio(kirtan_path, tts_path, output_path, fade_start=4000, kirtan_reduction=-15, tts_start_offset=0):
"""Merges kirtan and TTS audio with adjustable fade-in and offset."""
kirtan = AudioSegment.from_file(kirtan_path)
tts = AudioSegment.from_file(tts_path)
# Reduce kirtan volume after specified fade_start seconds
fade_point = min(fade_start, len(kirtan))
kirtan_fade = kirtan[:fade_point] + kirtan[fade_point:].apply_gain(kirtan_reduction)
# Overlay TTS over faded kirtan with offset adjustment
combined = kirtan_fade.overlay(tts, position=fade_point + tts_start_offset)
# Export merged file
combined.export(output_path, format="mp3")
def main():
st.title("Kirtan + TTS Audio Mixer with Adjustable Timing")
# Upload section
tts_file = st.file_uploader("Upload TTS Audio (MP3 or WAV)", type=["mp3", "wav"])
kirtan_option = st.selectbox("Select a Kirtan:", ["Kirtan 1", "Kirtan 2", "Kirtan 3"])
# Slider for user adjustment
fade_start = st.slider("Kirtan Fade Start (ms)", min_value=1000, max_value=10000, value=4000, step=500)
tts_start_offset = st.slider("TTS Start Offset (ms)", min_value=0, max_value=5000, value=0, step=100)
kirtan_reduction = st.slider("Kirtan Volume Reduction (dB)", min_value=-30, max_value=0, value=-15, step=1)
kirtan_files = {
"Kirtan 1": "kirtan1.mp3",
"Kirtan 2": "kirtan2.mp3",
"Kirtan 3": "kirtan3.mp3"
}
if tts_file and kirtan_option:
# Save uploaded TTS file
with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as temp_tts:
temp_tts.write(tts_file.read())
temp_tts_path = temp_tts.name
# Set paths
kirtan_path = kirtan_files[kirtan_option]
output_path = "merged_audio.mp3"
# Process audio with user-defined parameters
merge_audio(kirtan_path, temp_tts_path, output_path, fade_start, kirtan_reduction, tts_start_offset)
# Play and download merged file
st.audio(output_path, format='audio/mp3')
st.download_button("Download Merged Audio", output_path, file_name="final_audio.mp3")
# Cleanup temp files
os.remove(temp_tts_path)
if __name__ == "__main__":
main()
|