Skip to content

fix(tts): honor wav/flac output in OpenAI TTS provider instead of forcing mp3 #37337

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

Closed
MarvinFS wants to merge 1 commit into from
Closed

fix(tts): honor wav/flac output in OpenAI TTS provider instead of forcing mp3 #37337

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
10 changes: 9 additions & 1 deletion tools/tts_tool.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -997,9 +997,17 @@ def _generate_openai_tts(text: str, output_path: str, tts_config: Dict[str, Any]
base_url = oai_config.get("base_url", base_url)
speed = float(oai_config.get("speed", tts_config.get("speed", 1.0)))

# Determine response format from extension
# Determine response format from extension. Mirror the Mistral provider so a
# configured wav/flac output_format is honored instead of always forcing mp3.
# wav/flac are valid OpenAI audio.speech response_format values, and some
# OpenAI-compatible backends only implement native WAV (e.g. Chatterbox-TTS-Server),
# where forcing mp3 yields a hard "500: Failed to encode audio".
if output_path.endswith(".ogg"):
response_format = "opus"
elif output_path.endswith(".wav"):

@teknium1 teknium1 Jul 13, 2026

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Please normalize the suffix once (for example, Path(output_path).suffix.lower()) before this mapping. text_to_speech_tool() preserves a caller-provided path, so .WAV and .FLAC currently still fall through to mp3.

response_format = "wav"
elif output_path.endswith(".flac"):
response_format = "flac"
else:
response_format = "mp3"

Expand Down