Skip to content

fix: handle odd-length audio chunks in voice streaming (fixes #1824) #1928

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

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

fix: handle odd-length audio chunks in voice streaming (fixes #1824) #1928

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a0c221d
fix: handle odd-length audio chunks in voice streaming (fixes #1824)
Oct 18, 2025
ed0832a
Merge branch 'main' into fix/odd-length-audio-chunks-1824
gn00295120 Oct 24, 2025
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
11 changes: 10 additions & 1 deletion src/agents/voice/result.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,16 @@ async def _add_error(self, error: Exception):
def _transform_audio_buffer(
self, buffer: list[bytes], output_dtype: npt.DTypeLike
) -> npt.NDArray[np.int16 | np.float32]:
np_array = np.frombuffer(b"".join(buffer), dtype=np.int16)
# Combine all chunks
combined_buffer = b"".join(buffer)

# Pad with a zero byte if the buffer length is odd
# This is needed because np.frombuffer with dtype=np.int16 requires
# the buffer size to be a multiple of 2 bytes
if len(combined_buffer) % 2 != 0:
combined_buffer += b"\x00"
Comment on lines +94 to +98
Copy link

Copilot AI Oct 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[nitpick] Padding the trailing half-sample with 0 introduces synthesized audio data and can cause subtle artifacts in streaming scenarios. A more accurate approach is to carry over the trailing single byte to the next call (e.g., keep self._pending_byte, prepend it on the next invocation, and if the combined length is odd, stash the last byte instead of padding), preserving sample integrity without injecting data.

Copilot uses AI. Check for mistakes.
Comment on lines +94 to +98
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Avoid zero‑padding half samples midstream

Padding an odd-length audio buffer with b"\x00" before calling np.frombuffer causes a permanent byte shift when the odd length occurs before the final chunk. In normal streaming, a TTS provider may emit an odd-sized chunk whose last byte is just the first half of a 16‑bit sample; zero‑padding here turns that half sample into its own frame and the next chunk’s first byte becomes the low byte of a new sample. From that point the stream is misaligned and produces distorted audio rather than the intended samples. Instead, carry the extra byte forward and prepend it to the next chunk so that sample boundaries remain intact.

Useful? React with 👍 / 👎.


Comment on lines +91 to +99
Copy link

Copilot AI Oct 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[nitpick] This builds combined_buffer (size N) and then, on odd lengths, allocates and copies again to append one byte, resulting in two large allocations. You can avoid the extra copy by appending the padding byte to the list of chunks and performing a single join, e.g.:
total_len = sum(len(c) for c in buffer)
if total_len % 2 != 0:
buffer = [*buffer, b"\x00"]
np_array = np.frombuffer(b"".join(buffer), dtype=np.int16).

Suggested change
# Combine all chunks
combined_buffer = b"".join(buffer)
# Pad with a zero byte if the buffer length is odd
# This is needed because np.frombuffer with dtype=np.int16 requires
# the buffer size to be a multiple of 2 bytes
if len(combined_buffer) % 2 != 0:
combined_buffer += b"\x00"
# Combine all chunks, padding with a zero byte if the total length is odd
total_len = sum(len(c) for c in buffer)
if total_len % 2 != 0:
buffer = [*buffer, b"\x00"]
combined_buffer = b"".join(buffer)

Copilot uses AI. Check for mistakes.
np_array = np.frombuffer(combined_buffer, dtype=np.int16)

if output_dtype == np.int16:
return np_array
Comment on lines 102 to 103
Copy link

Copilot AI Oct 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Comparing output_dtype directly to np.int16 may fail for equivalent values like 'int16' or np.dtype('int16'). Normalize the dtype for robust comparison:
if np.dtype(output_dtype) == np.dtype(np.int16):
return np_array.

Copilot uses AI. Check for mistakes.
Expand Down