Skip to content

Trim audio to video when saving video. #9617

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
comfyanonymous merged 1 commit into from
Aug 29, 2025
Merged

Trim audio to video when saving video. #9617

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
36 changes: 10 additions & 26 deletions comfy_api/latest/_input_impl/video_types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
import io
import json
import numpy as np
import math
import torch
from comfy_api.latest._util import VideoContainer, VideoCodec, VideoComponents

Expand Down Expand Up @@ -282,8 +283,6 @@ def save_to(
if self.__components.audio:
audio_sample_rate = int(self.__components.audio['sample_rate'])
audio_stream = output.add_stream('aac', rate=audio_sample_rate)
audio_stream.sample_rate = audio_sample_rate
audio_stream.format = 'fltp'

# Encode video
for i, frame in enumerate(self.__components.images):
Expand All @@ -298,27 +297,12 @@ def save_to(
output.mux(packet)

if audio_stream and self.__components.audio:
# Encode audio
samples_per_frame = int(audio_sample_rate / frame_rate)
num_frames = self.__components.audio['waveform'].shape[2] // samples_per_frame
for i in range(num_frames):
start = i * samples_per_frame
end = start + samples_per_frame
# TODO(Feature) - Add support for stereo audio
chunk = (
self.__components.audio["waveform"][0, 0, start:end]
.unsqueeze(0)
.contiguous()
.numpy()
)
audio_frame = av.AudioFrame.from_ndarray(chunk, format='fltp', layout='mono')
audio_frame.sample_rate = audio_sample_rate
audio_frame.pts = i * samples_per_frame
for packet in audio_stream.encode(audio_frame):
output.mux(packet)

# Flush audio
for packet in audio_stream.encode(None):
output.mux(packet)


waveform = self.__components.audio['waveform']
waveform = waveform[:, :, :math.ceil((audio_sample_rate / frame_rate) * self.__components.images.shape[0])]
frame = av.AudioFrame.from_ndarray(waveform.movedim(2, 1).reshape(1, -1).float().numpy(), format='flt', layout='mono' if waveform.shape[1] == 1 else 'stereo')
frame.sample_rate = audio_sample_rate
frame.pts = 0
output.mux(audio_stream.encode(frame))

# Flush encoder
output.mux(audio_stream.encode(None))
Loading