fix: play returned TTS audio path in CLI voice mode

This commit is contained in:
YAMAGUCHI Seiji 2026-06-10 07:31:50 +09:00 • committed by Teknium
parent af7205bea5
commit 1182efa0a8
4 changed files with 73 additions and 17 deletions

26
cli.py
View file

@ -12000,17 +12000,27 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin, CLIBillingMixin):
f"tts_{time.strftime('%Y%m%d_%H%M%S')}.mp3",
)
text_to_speech_tool(text=tts_text, output_path=mp3_path)
raw_result = text_to_speech_tool(text=tts_text, output_path=mp3_path)
try:
tts_result = json.loads(raw_result) if isinstance(raw_result, str) else {}
except Exception:
tts_result = {}
audio_path = tts_result.get("file_path") or mp3_path
# Play the MP3 directly (the TTS tool returns OGG path but MP3 still exists)
if os.path.isfile(mp3_path) and os.path.getsize(mp3_path) > 0:
play_audio_file(mp3_path)
# Play the actual file returned by the TTS provider. Command
# providers may keep native formats such as FLAC/WAV instead of
# writing the requested MP3 path.
if os.path.isfile(audio_path) and os.path.getsize(audio_path) > 0:
play_audio_file(audio_path)
# Clean up
try:
os.unlink(mp3_path)
ogg_path = mp3_path.rsplit(".", 1)[0] + ".ogg"
if os.path.isfile(ogg_path):
os.unlink(ogg_path)
cleanup_paths = {audio_path, mp3_path}
for path in list(cleanup_paths):
ogg_path = path.rsplit(".", 1)[0] + ".ogg"
cleanup_paths.add(ogg_path)
for path in cleanup_paths:
if os.path.isfile(path):
os.unlink(path)
except OSError:
pass
except Exception as e: