白嫖微软tts合成
By
xuncv
at 2023-04-22 • 0人收藏 • 873人看过
因为使用的免费接口，代码仅适合临时应急或体验微软的tts服务。微软官方也不建议使用rest接口
rest接口返回的是字节数组，也就是音频数据，因此库选用了比较底层的web.rest.client，更加灵活
import console; import string.templateimport web.rest.clientweb.rest.jsonClientvar ssmlTemp = string.template()ssmlTemp.template = /***<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-US"> <voice name="zh-CN-YunxiNeural"> <mstts:express-as > <prosody rate="10.000000000000009%" pitch="0%"> ${text} </prosody> </mstts:express-as> </voice> </speak>***/var ssml = ssmlTemp.format( text = "aardio 在诞生之初就设计了良好的架构与语法。正因如此，aardio 历经17年发展，日新月异，每一年都会带来大量的更新扩展，但仍然能保持最初简洁高效的结构与语法，即使是最早的 aardio 源代码仍然能不经修改在最新版本开发环境中完美运行。";)client = web.rest.client()client.addHeaders = { authority: "southeastasia.api.speech.microsoft.com", accept: "*/*", "accept-language": "zh-CN,zh;q=0.9", customvoiceconnectionid: "d8a3a480-dd87-11ed-8758-97b5a7fbfaf6", origin: "https://speech.microsoft.com", "sec-ch-ua": '"Google Chrome";v="111", "Not(A:Brand";v="8", "Chromium";v="111"', "sec-ch-ua-mobile": "?0", "sec-ch-ua-platform": '"Windows"', "sec-fetch-dest": "empty", "sec-fetch-mode": "cors", "sec-fetch-site": "same-site", "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36", "content-type": "application/json",}api = client.api("https://southeastasia.api.speech.microsoft.com/accfreetrial/texttospeech/acc/v3.0-beta1")console.log("语音合成中")var res,e,c = api.vcg.speak.post(web.json.stringify({ ssml = ssml; ttsAudioFormat = "audio-24khz-160kbitrate-mono-mp3"; offsetInPlainText = 0; properties = { SpeakTriggerSource = "AccTuningPagePlayButton"; }; }))if(res){ string.save("D:\test.mp3",res ) }console.pause()
3 个回复 | 最后更新于 2023-04-23
登录后方可回帖
import console; import string.template import web.rest.client var ssmlTemp = string.template() ssmlTemp.template = /*** <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-US"> <voice name="zh-CN-YunxiNeural"> <mstts:express-as > <prosody rate="10.000000000000009%" pitch="0%"> ${text} </prosody> </mstts:express-as> </voice> </speak> ***/ var ssml = ssmlTemp.format( text = "aardio 在诞生之初就设计了良好的架构与语法。正因如此，aardio 历经17年发展，日新月异，每一年都会带来大量的更新扩展，但仍然能保持最初简洁高效的结构与语法，即使是最早的 aardio 源代码仍然能不经修改在最新版本开发环境中完美运行。"; ) client = web.rest.client() client.addHeaders = { authority: "southeastasia.api.speech.microsoft.com", accept: "*/*", "accept-language": "zh-CN,zh;q=0.9", customvoiceconnectionid: "d8a3a480-dd87-11ed-8758-97b5a7fbfaf6", origin: "https://speech.microsoft.com", "sec-ch-ua": '"Google Chrome";v="111", "Not(A:Brand";v="8", "Chromium";v="111"', "sec-ch-ua-mobile": "?0", "sec-ch-ua-platform": '"Windows"', "sec-fetch-dest": "empty", "sec-fetch-mode": "cors", "sec-fetch-site": "same-site", "user-agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36", "content-type": "application/json", } api = client.api("https://southeastasia.api.speech.microsoft.com/accfreetrial/texttospeech/acc/v3.0-beta1") console.log("语音合成中") var res,e,c = api.vcg.speak.post(web.json.stringify( { ssml = ssml; ttsAudioFormat = "audio-24khz-160kbitrate-mono-mp3"; offsetInPlainText = 0; properties = { SpeakTriggerSource = "AccTuningPagePlayButton"; }; })) if(res){ string.save("D:\test.mp3",res ) } console.pause()