你当前正在访问 Microsoft Azure Global Edition 技术文档网站。 如果需要访问由世纪互联运营的 Microsoft Azure 中国技术文档网站，请访问 https://docs.azure.cn。

将快速听录 API（预览版）与 Azure AI 语音配合使用

  • 项目

注意

此功能目前处于公开预览状态。 此预览版没有附带服务级别协议，建议不要用于生产工作负载。 某些功能可能不受支持或者受限。 有关详细信息，请参阅 Microsoft Azure 预览版补充使用条款。

快速听录 API 只能通过语音转文本 REST API 版本 2024-05-15-preview 使用。 此预览版本可能会更改，不建议用于生产。 它将在后续预览版本或 API 正式发布 (GA) 后 90 天后停用，恕不另行通知。

快速听录 API 用于听录音频文件，同步返回结果，速度比实时音频快得多。 在需要尽快获得音频录制脚本且可预测延迟的情况下使用快速听录，例如：

  • 快速音频或视频听录、字幕和编辑。
  • 视频翻译

提示

在Azure AI Studio中试用快速听录。

先决条件

  • 快速听录 API 可用的某个区域中的 Azure AI 语音资源。 受支持的区域包括：印度中部、美国东部、东南亚和西欧。 有关其他语音服务功能支持的区域的详细信息，请参阅语音服务区域。
  • 音频文件（长度小于 2 小时且大小小于 200 MB）采用批量听录 API 支持的格式和编解码器之一。 有关受支持的音频格式的详细信息，请参阅受支持的音频格式。

使用快速听录 API

快速听录 API 是一种 REST API，它使用多部分/表单数据提交音频文件以进行听录。 API 同步返回听录结果。

根据以下说明构造请求正文：

  • 设置所需的 locales 属性。 此值应与要听录的音频数据的预期区域设置相匹配。 受支持的区域设置包括：en-US、es-ES、es-MX、fr-FR、hi-IN、it、ja-JP、ko-KR、pt-BR 和 zh-CN。 每个听录请求只能指定一个区域设置。
  • （可选）设置profanityFilterMode属性以指定如何处理识别结果中的亵渎内容。 接受的值为 None（禁用不雅内容筛选）、Masked（将不雅内容替换为星号）、Removed（从结果中删除所有不雅内容）或 Tags（添加不雅内容标记）。 默认值为 Masked。 profanityFilterMode属性的工作方式与通过批量听录 API的工作方式相同。
  • （可选）设置channels属性以指定要单独听录的通道的从零开始的索引。 如果未指定，则合并并听录多个通道。 最多支持两个通道。 如果要单独从立体声音频文件听录通道，则需要在此处指定[0,1]。 否则，立体声音频将合并为单声道，单声道音频将按原样保留，并且只会听录单个通道。 在后一种情况下，输出没有听录文本的通道索引，因为只听录了单个音频流。

使用音频文件和请求正文属性向transcriptions终结点发出多部分/表单数据 POST 请求。 以下示例演示了如何使用快速听录 API 创建听录。

  • 将 YourSubscriptionKey 替换为语音资源密钥。
  • 将 YourServiceRegion 替换为你所在的语音资源区域。
  • 将YourAudioFile替换为音频文件的路径。
  • 如前所述设置表单定义属性。
curl --location 'https://YourServiceRegion.api.cognitive.microsoft.com/speechtotext/transcriptions:transcribe?api-version=2024-05-15-preview' \
--header 'Content-Type: multipart/form-data' \
--header 'Accept: application/json' \
--header 'Ocp-Apim-Subscription-Key: YourSubscriptionKey' \
--form 'audio=@"YourAudioFile"' \
--form 'definition="{
    \"locales\":[\"en-US\"], 
    \"profanityFilterMode\": \"Masked\", 
    \"channels\": [0,1]}"'

响应将包括duration、channel等。 combinedPhrases属性分别包含每个通道的完整听录。 例如，第一个说话人所说的所有内容都位于combinedPhrases数组的第一个元素中，第二个说话人所说的所有内容都位于数组的第二个元素中。

{
	"duration": 185079,
	"combinedPhrases": [
		{
			"channel": 0,
			"text": "Hello. Thank you for calling Contoso. Who am I speaking with today? Hi, Mary. Are you calling because you need health insurance? Great. If you can answer a few questions, we can get you signed up in the Jiffy. So what's your full name? Got it. And what's the best callback number in case we get disconnected? Yep, that'll be fine. Got it. So to confirm, it's 234-554-9312. Excellent. Let's get some additional information for your application. Do you have a job? OK, so then you have a Social Security number as well. OK, and what is your Social Security number please? Sorry, what was that, a 25 or a 225? You cut out for a bit. Alright, thank you so much. And could I have your e-mail address please? Great. Uh That is the last question. So let me take your information and I'll be able to get you signed up right away. Thank you for calling Contoso and I'll be able to get you signed up immediately. One of our agents will call you back in about 24 hours or so to confirm your application. Absolutely. If you need anything else, please give us a call at 1-800-555-5564, extension 123. Thank you very much for calling Contoso. Uh Yes, of course. So the default is a digital membership card, but we can send you a physical card if you prefer. Uh, yeah. Absolutely. I've made a note on your file. You're very welcome. Thank you for calling Contoso and have a great day."
		},
		{
			"channel": 1,
			"text": "Hi, my name is Mary Rondo. I'm trying to enroll myself with Contuso. Yes, yeah, I'm calling to sign up for insurance. Okay. So Mary Beth Rondo, last name is R like Romeo, O like Ocean, N like Nancy D, D like Dog, and O like Ocean again. Rondo. I only have a cell phone so I can give you that. Sure, so it's 234-554 and then 9312. Yep, that's right. Uh Yes, I am self-employed. Yes, I do. Uh Sure, so it's 412256789. It's double two, so 412, then another two, then five. Yeah, it's maryrondo@gmail.com. So my first and last name at gmail.com. No periods, no dashes. That was quick. Thank you. Actually, so I have one more question. I'm curious, will I be getting a physical card as proof of coverage? uh Yes. Could you please mail it to me when it's ready? I'd like to have it shipped to, are you ready for my address? So it's 2660 Unit A on Maple Avenue SE, Lansing, and then zip code is 48823. Awesome. Thanks so much."
		}
	],
	"phrases": [
		{
			"channel": 0,
			"offset": 720,
			"duration": 480,
			"text": "Hello.",
			"words": [
				{
					"text": "Hello.",
					"offset": 720,
					"duration": 480
				}
			],
			"locale": "en-US",
			"confidence": 0.9177142
		},
		{
			"channel": 0,
			"offset": 1200,
			"duration": 1120,
			"text": "Thank you for calling Contoso.",
			"words": [
				{
					"text": "Thank",
					"offset": 1200,
					"duration": 200
				},
				{
					"text": "you",
					"offset": 1400,
					"duration": 80
				},
				{
					"text": "for",
					"offset": 1480,
					"duration": 120
				},
				{
					"text": "calling",
					"offset": 1600,
					"duration": 240
				},
				{
					"text": "Contoso.",
					"offset": 1840,
					"duration": 480
				}
			],
			"locale": "en-US",
			"confidence": 0.9177142
		},
		{
			"channel": 0,
			"offset": 2320,
			"duration": 1120,
			"text": "Who am I speaking with today?",
			"words": [
				{
					"text": "Who",
					"offset": 2320,
					"duration": 160
				},
				{
					"text": "am",
					"offset": 2480,
					"duration": 80
				},
				{
					"text": "I",
					"offset": 2560,
					"duration": 80
				},
				{
					"text": "speaking",
					"offset": 2640,
					"duration": 320
				},
				{
					"text": "with",
					"offset": 2960,
					"duration": 160
				},
				{
					"text": "today?",
					"offset": 3120,
					"duration": 320
				}
			],
			"locale": "en-US",
			"confidence": 0.9177142
		},
        // More transcription results removed for brevity
        // {...},
		{
			"channel": 1,
			"offset": 4480,
			"duration": 1600,
			"text": "Hi, my name is Mary Rondo.",
			"words": [
				{
					"text": "Hi,",
					"offset": 4480,
					"duration": 400
				},
				{
					"text": "my",
					"offset": 4880,
					"duration": 120
				},
				{
					"text": "name",
					"offset": 5000,
					"duration": 120
				},
				{
					"text": "is",
					"offset": 5120,
					"duration": 160
				},
				{
					"text": "Mary",
					"offset": 5280,
					"duration": 240
				},
				{
					"text": "Rondo.",
					"offset": 5520,
					"duration": 560
				}
			],
			"locale": "en-US",
			"confidence": 0.8989456
		},
		{
			"channel": 1,
			"offset": 6080,
			"duration": 1920,
			"text": "I'm trying to enroll myself with Contuso.",
			"words": [
				{
					"text": "I'm",
					"offset": 6080,
					"duration": 160
				},
				{
					"text": "trying",
					"offset": 6240,
					"duration": 200
				},
				{
					"text": "to",
					"offset": 6440,
					"duration": 80
				},
				{
					"text": "enroll",
					"offset": 6520,
					"duration": 200
				},
				{
					"text": "myself",
					"offset": 6720,
					"duration": 360
				},
				{
					"text": "with",
					"offset": 7080,
					"duration": 120
				},
				{
					"text": "Contuso.",
					"offset": 7200,
					"duration": 800
				}
			],
			"locale": "en-US",
			"confidence": 0.8989456
		},
        // More transcription results removed for brevity
        // {...},
	]
}

相关内容