From 145cbc21527d68613c6f4d0babe52763a8c7191f Mon Sep 17 00:00:00 2001
From: yuhongxiao <hongxiao.yu@aminer.cn>
Date: Fri, 5 Sep 2025 16:44:31 +0800
Subject: [PATCH] add tts param volume and speed

---
 src/zai/api_resource/audio/audio.py   | 4 ++++
 tests/integration_tests/test_audio.py | 7 +++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/src/zai/api_resource/audio/audio.py b/src/zai/api_resource/audio/audio.py
index 9523f47..92fe520 100644
--- a/src/zai/api_resource/audio/audio.py
+++ b/src/zai/api_resource/audio/audio.py
@@ -55,6 +55,8 @@ def speech(
 		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 @@ def speech(
 				'sensitive_word_check': sensitive_word_check,
 				'request_id': request_id,
 				'user_id': user_id,
+				'speed': speed,
+				'volume': volume,
 			}
 		)
 		return self._post(
diff --git a/tests/integration_tests/test_audio.py b/tests/integration_tests/test_audio.py
index e143571..420f19b 100644
--- a/tests/integration_tests/test_audio.py
+++ b/tests/integration_tests/test_audio.py
@@ -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)