wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update src/pipecat/services/minimax/tts.py

Browse Source 
Co-authored-by: Mark Backman <mark@daily.co>

add warning
This commit is contained in:
Vanessa Pyne
2025-11-05 09:11:55 -06:00
committed by vipyne
parent ce09c6f6ff
commit 13f1507c06
1 changed files with 15 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
src/pipecat/services/minimax/tts.py
View File

@@ -111,9 +111,13 @@ class MiniMaxHttpTTSService(TTSService):
emotion: Emotional tone (options: "happy", "sad", "angry", "fearful", emotion: Emotional tone (options: "happy", "sad", "angry", "fearful",
"disgusted", "surprised", "calm", "fluent"). "disgusted", "surprised", "calm", "fluent").
english_normalization: Deprecated; use `text_normalization` instead english_normalization: Deprecated; use `text_normalization` instead
.. deprecated:: 0.0.93
The `english_normalization` parameter is deprecated and will be removed in a future version.
Use the `text_normalization` parameter instead.
text_normalization: Enable text normalization (Chinese/English). text_normalization: Enable text normalization (Chinese/English).
latex_read: Enable LaTeX formula reading. latex_read: Enable LaTeX formula reading.
force_cbr: Enable Constant Bitrate (CBR) for audio encoding (MP3 only).
exclude_aggregated_audio: Whether to exclude aggregated audio in final chunk. exclude_aggregated_audio: Whether to exclude aggregated audio in final chunk.
subtitle_enable: Enable subtitle generation (non-streaming only). subtitle_enable: Enable subtitle generation (non-streaming only).
subtitle_type: Subtitle timestamp granularity (options: "word", "sentence"). subtitle_type: Subtitle timestamp granularity (options: "word", "sentence").
@@ -128,7 +132,6 @@ class MiniMaxHttpTTSService(TTSService):
english_normalization: Optional[bool] = None # Deprecated english_normalization: Optional[bool] = None # Deprecated
text_normalization: Optional[bool] = None text_normalization: Optional[bool] = None
latex_read: Optional[bool] = None latex_read: Optional[bool] = None
force_cbr: Optional[bool] = None
exclude_aggregated_audio: Optional[bool] = None exclude_aggregated_audio: Optional[bool] = None
subtitle_enable: Optional[bool] = None subtitle_enable: Optional[bool] = None
subtitle_type: Optional[str] = "sentence" subtitle_type: Optional[str] = "sentence"
@@ -207,20 +210,9 @@ class MiniMaxHttpTTSService(TTSService):
if service_lang: if service_lang:
self._settings["language_boost"] = service_lang self._settings["language_boost"] = service_lang
# Validate language-model compatibility
# Filipino, Tamil, Persian only supported by speech-2.6-* models
if params.language in {Language.FA, Language.FIL, Language.TA}:
if not model.startswith("speech-2.6"):
logger.warning(
f"Language {params.language.value} ({service_lang}) is only supported by "
f"speech-2.6-hd and speech-2.6-turbo models. "
f"Current model '{model}' may not support this language. "
f"Consider using 'speech-2.6-turbo' or 'speech-2.6-hd'."
)
# Add optional emotion if provided # Add optional emotion if provided
if params.emotion: if params.emotion:
# Validate emotion is in the supported list (updated per official docs) # Validate emotion is in the supported list
supported_emotions = [ supported_emotions = [
"happy", "happy",
"sad", "sad",
@@ -240,9 +232,14 @@ class MiniMaxHttpTTSService(TTSService):
# If `english_normalization`, add `text_normalization` and print warning # If `english_normalization`, add `text_normalization` and print warning
if params.english_normalization is not None: if params.english_normalization is not None:
logger.warning( import warnings
"Parameter `english_normalization` is deprecated and will be removed in a future version. Use `text_normalization` instead."
) with warnings.catch_warnings():
warnings.simplefilter("always")
warnings.warn(
"Parameter `english_normalization` is deprecated and will be removed in a future version. Use `text_normalization` instead.",
DeprecationWarning,
)
self._settings["voice_setting"]["text_normalization"] = params.english_normalization self._settings["voice_setting"]["text_normalization"] = params.english_normalization
# Add text_normalization if provided (corrected parameter name) # Add text_normalization if provided (corrected parameter name)
@@ -253,10 +250,6 @@ class MiniMaxHttpTTSService(TTSService):
if params.latex_read is not None: if params.latex_read is not None:
self._settings["voice_setting"]["latex_read"] = params.latex_read self._settings["voice_setting"]["latex_read"] = params.latex_read
# Add force_cbr if provided (for MP3 format only)
if params.force_cbr is not None:
self._settings["audio_setting"]["force_cbr"] = params.force_cbr
# Add subtitle settings if provided # Add subtitle settings if provided
if params.subtitle_enable is not None: if params.subtitle_enable is not None:
# Note: subtitle_enable only works in non-streaming mode (stream=false) # Note: subtitle_enable only works in non-streaming mode (stream=false)
@@ -334,7 +327,7 @@ class MiniMaxHttpTTSService(TTSService):
""" """
await super().start(frame) await super().start(frame)
self._settings["audio_setting"]["sample_rate"] = self.sample_rate self._settings["audio_setting"]["sample_rate"] = self.sample_rate
logger.debug(f"MiniMax TTS initialized with sample_rate={self.sample_rate}") logger.debug(f"MiniMax TTS initialized with sample_rate: {self.sample_rate}")
@traced_tts @traced_tts
async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]: async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
@@ -414,28 +407,6 @@ class MiniMaxHttpTTSService(TTSService):
if chunk_count == 1: if chunk_count == 1:
logger.trace(f"Raw buffer content: {buffer[:200]}") # First 200 bytes logger.trace(f"Raw buffer content: {buffer[:200]}") # First 200 bytes
# Check if first chunk is a direct JSON error (not streaming format)
if not buffer.startswith(b"data:"):
try:
error_data = json.loads(buffer.decode("utf-8"))
base_resp = error_data.get("base_resp", {})
status_code = base_resp.get("status_code", 0)
if status_code != 0:
# This is a non-streaming error response
status_msg = base_resp.get("status_msg", "Unknown error")
error_message = (
f"MiniMax TTS API error: status_code={status_code}"
f"status_msg={status_msg}"
)
logger.error(error_message)
yield ErrorFrame(error=error_message)
return
except (json.JSONDecodeError, UnicodeDecodeError):
# Not a valid JSON, continue with streaming processing
pass
# Find complete data blocks # Find complete data blocks
while b"data:" in buffer: while b"data:" in buffer:
start = buffer.find(b"data:") start = buffer.find(b"data:")