feat: add tts param volume and speed (#34)

Co-authored-by: yuhongxiao <hongxiao.yu@aminer.cn>
Co-authored-by: Tom <tomsun28@outlook.com>
This commit is contained in:
iceAndFireisFailed 2025-09-09 19:28:41 +08:00 committed by GitHub
parent e7e2af0727
commit 372d99cc4d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 9 additions and 2 deletions

View file

@ -55,6 +55,8 @@ class Audio(BaseAPI):
extra_headers: Headers | None = None,
extra_body: Body | None = None,
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
speed: float | None = 1.0,
volume: float | None = 1.0,
) -> HttpxBinaryResponseContent:
"""
Generate speech audio from text input
@ -80,6 +82,8 @@ class Audio(BaseAPI):
'sensitive_word_check': sensitive_word_check,
'request_id': request_id,
'user_id': user_id,
'speed': speed,
'volume': volume,
}
)
return self._post(

View file

@ -10,12 +10,15 @@ def test_audio_speech(logging_conf):
logging.config.dictConfig(logging_conf) # type: ignore
client = ZaiClient() # Fill in your own API Key
try:
speech_file_path = Path(__file__).parent / 'asr1.wav'
speech_file_path = Path(__file__).parent / 'asr1.pcm'
response = client.audio.speech(
model='cogtts',
input='Hello, welcome to Z.ai Open Platform',
voice='female',
response_format='wav',
response_format='pcm',
encode_format='hex',
speed=1.0,
volume=1.0,
)
response.stream_to_file(speech_file_path)