File size: 1,032 Bytes
ad6d2e0 81567e9 ad6d2e0 81567e9 ad6d2e0 53ec323 81567e9 81dba60 81567e9 |
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 |
from fastrtc import Stream, ReplyOnPause
import numpy as np
from pydub import AudioSegment
from pydub.utils import which
import gradio as gr
AudioSegment.ffmpeg = which("ffmpeg")
def echo(audio: tuple[int, np.ndarray]) -> tuple[int, np.ndarray]:
yield audio
stream = Stream(ReplyOnPause(echo), modality="audio", mode="send-receive")
def process_audio(audio_input):
# audio_input is received as a Gradio Audio object, containing a tuple of (sample_rate, numpy array)
sample_rate, audio_data = audio_input
# Process audio through the stream
processed_sample_rate, processed_audio = echo((sample_rate, audio_data))
# Return processed audio to Gradio for output
return processed_sample_rate, processed_audio
interface = gr.Interface(
fn=process_audio, # The function to process audio
inputs=gr.Audio(type="numpy"), # Microphone input (audio)
outputs=gr.Audio(type="numpy"), # Audio output (processed)
live=True # Make the processing live (if needed)
)
interface.launch()
|