Skip to content

[pull] master from comfyanonymous:master #158

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
pull merged 1 commit into from
Jul 6, 2025
Merged

[pull] master from comfyanonymous:master #158

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
18 changes: 3 additions & 15 deletions comfy_extras/nodes_audio.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -133,14 +133,6 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
if sample_rate != audio["sample_rate"]:
waveform = torchaudio.functional.resample(waveform, audio["sample_rate"], sample_rate)

# Create in-memory WAV buffer
wav_buffer = io.BytesIO()
torchaudio.save(wav_buffer, waveform, sample_rate, format="WAV")
wav_buffer.seek(0) # Rewind for reading

# Use PyAV to convert and add metadata
input_container = av.open(wav_buffer)

# Create output with specified format
output_buffer = io.BytesIO()
output_container = av.open(output_buffer, mode='w', format=format)
Expand All @@ -150,7 +142,6 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
output_container.metadata[key] = value

# Set up the output stream with appropriate properties
input_container.streams.audio[0]
if format == "opus":
out_stream = output_container.add_stream("libopus", rate=sample_rate)
if quality == "64k":
Expand All @@ -175,18 +166,15 @@ def save_audio(self, audio, filename_prefix="ComfyUI", format="flac", prompt=Non
else: #format == "flac":
out_stream = output_container.add_stream("flac", rate=sample_rate)


# Copy frames from input to output
for frame in input_container.decode(audio=0):
frame.pts = None # Let PyAV handle timestamps
output_container.mux(out_stream.encode(frame))
frame = av.AudioFrame.from_ndarray(waveform.movedim(0, 1).reshape(1, -1).float().numpy(), format='flt', layout='mono' if waveform.shape[0] == 1 else 'stereo')
frame.sample_rate = sample_rate
output_container.mux(out_stream.encode(frame))

# Flush encoder
output_container.mux(out_stream.encode(None))

# Close containers
output_container.close()
input_container.close()

# Write the output to file
output_buffer.seek(0)
Expand Down
Loading