阿里云智能语音服务常见问题
- 服务开通问题
- SDK调用问题
- 音频格式问题
- 服务使用问题
1. 服务开通问题
访问阿里云官网—>数加—>
智能语音交互。点击获取使用资格,注册信息。等待审核。审核通过后会收到邮件和短信提醒。然后再返回
智能语音交互页面,点击进入管理控制台。开通智能语音交互公测。
1.1 Q:我开通了服务,使用不了?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A:请确认是否在控制台开通智能语音交互公测。
1.2 Q: 我找不到Access id 和Access Secret 在哪里?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 请按照[账号和服务申请](https://help.aliyun.com/document_detail/30437.html)文档中的步骤创建子账号获得Access id 和Access Secret。
1.3 Q: Appkey 怎么获取?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 接入每个智能语音服务都需要选择对应的appKey,具体可选列表请查看接入服务帮助文档的简介页面。
1.4 Q:申请公测审核时间?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 我们会有专人负责审批公测申请,一般3个工作日内会审核通过。
2. 服务使用问题
2.1 Q: 服务协议和接口?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: - 智能语音服务sdk 大多数基于websocket协议实现,由于支持语音实时发送的长连接模式,我们在实时场景没有restful接口。
- - 离线文件转写支持restful接口服务。
2.2 Q: 识别不准确?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A:我们即将上线热词功能,用户可以自定义常用词,可以快速、实时提高准确率。
- A: 可以联系我们商务同学,对于特定场景提供定制优化。
2.3 Q: 收费标准?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 公测阶段10路并发以内试用不收费。
2.4 Q: 调用次数有没有限制?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 公测阶段调用次数没有限制。
2.5 Q:服务请求时长限制?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 一句话识别支持60s以内的实时语音。实时语音识别不限制时长。
3. SDK调用问题
错误码列表:
3.1 Q: 错误码400,msg=check text frame params failed?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 请求字段有错误。 如appkey填错了、没有设置access信息等等。 注意查看请求参数。
3.2 Q:离线文件转写 错误码400,file download failed。<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A:查看出问题的文件的oss地址,在浏览器是否能够直接访问?开放访问权限是否开通。
3.3 Q: 错误码403.<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A:确认是否开通语音服务,参考问题1.1 。确认地址:https://data.aliyun.com/product/nls 。
3.4 Q:英文识别支持么?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A:实时语音支持英文识别,appkey:nls-service-en。
4. 音频格式问题
智能语音服务公测阶段:
- 一句话识别和长语音识别支持16k/8k采样率,16bit单声道pcm/wav 语音输入。
- 离线文件识别支持16k/8k采样率,单/双声道,aLaw/linear, pcm/wav/mp3 语音输入。
- Android和iOS SDK支持OPUS压缩格式编码。
4.1 Q:aac,amr等其他格式是否支持?<divre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; margin: 0px 0px 16px; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 目前我们暂不支持以上多种格式的编解码,用户需要自己转码后使用阿里云智能语音交互。
4.2 Q:我的采样率是44.1kHz,可以直接识别么?<pre style='background: rgb(246, 246, 246); font: 12px/1.6 "YaHei Consolas Hybrid", Consolas, "Meiryo UI", "Malgun Gothic", "Segoe UI", "Trebuchet MS", Helvetica, monospace, monospace; padding: 10px; outline: 0px; border-radius: 3px; border: 1px solid rgb(221, 221, 221); color: rgb(51, 51, 51); text-transform: none; text-indent: 0px; letter-spacing: normal; overflow: auto; margin-top: 0px; margin-right: 0px; margin-bottom: 0px !important; margin-left: 0px; word-spacing: 0px; white-space: pre-wrap; word-wrap: break-word; box-sizing: border-box; orphans: 2; widows: 2; font-size-adjust: none; font-stretch: normal; -webkit-text-stroke-width: 0px; text-decoration-style: initial; text-decoration-color: initial;' prettyprinted?="" linenums="">
- A: 需要用户降采样至16kHz。