本地录制声音传给阿里音频理解模型，实时流式返回回答结果：
import dashscope
messages = [
{
"role": "user",
"content": [
{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"},
{"text": "这段音频在说什么?"}
]
}
]
response = dashscope.MultiModalConversation.call(
model="qwen-audio-turbo-latest",
messages=messages,
stream=True,
incremental_output=True,
result_format="message"
)
for chunk in response:
print(chunk)https://help.aliyun.com/zh/model-studio/user-guide/audio-language-model
websocket实时语音识别
https://help.aliyun.com/zh/model-studio/developer-reference/websocket-for-paraformer-real-time-service
网友回复
我知道答案，我要回答
私活外包
