问题描述
SSML 尝试过-
<speak xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="http://www.w3.org/2001/mstts" xmlns:emo="http://www.w3.org/2009/10/emotionml" version="1.0" xml:lang="en-IN"> <mstts:backgroundaudio src="https://cdn.yellowmessenger.com/3Ix9bm4Blriv1620110811289.wav" volume="0.3" fadein="3000" fadeout="4000"/><voice name="Microsoft Server Speech Text to Speech Voice (en-IN,NeerjaNeural)"><prosody rate="-10.00%" volume="+30.00%" contour="(27%,-13%) (49%,+7%) (73%,-11%)">Hi,Good Morning. Welcome! </prosody><prosody rate="-10.00%" volume="+30.00%" contour="(13%,-7%) (26%,+12%) (60%,-14%) (76%,+15%) (90%,-6%)">I can help you answer your queries regarding place an order,locate your order and do much more.</prosody><prosody rate="+10.00%" volume="+30.00%" contour="(18%,-6%) (40%,+12%) (64%,-10%)"> Please note that this call might be recorded for internal quality and training purposes.</prosody><prosody volume="+30.00%" contour="(41%,+6%) (74%,-26%)">Let us get started</prosody></voice></speak>
解决方法
这是使用语音合成标记语言 (SSML) 改进合成的 doc。