![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service.png\")
<\/p>\n<\/p>\n
Azure provides Speech Services that let developers add advanced speech features to achieve complex functionality, including Speech-to-Text. With Azure Speech Services, we can convert speech to text.<\/p>\n
\u00a0In this blog post, let us check how the conversion from speech to text using Azure Speech Service<\/strong> in a Power Automate flow is done. The following steps can help achieve this requirement.<\/p>\n Recently, we got a requirement to transcribe audio attachments when an email is received with attachments in the shared mailbox and send back transcribed text.<\/p>\n Create an \u2018Automated\u2019 flow using the trigger \u201cWhen a new email arrives in a shared mailbox (V2)\u201d<\/p>\n Add the \u2018Initialize variable\u2019 action to store the transcribed text of the audio attachment for further use.<\/p>\n Add the \u2018Initialize variable\u2019 action to store the content of the audio attachment for further use.<\/p>\n Now, proceed to get the attached attachments of the received email. Utilize an ‘Apply to Each’ action to iterate through each attachment of an email and within that add a \u2018Get Attachments (V2)\u2019 action to get the current attachment of an email.<\/p>\n Expressions from the above image:<\/p>\n Add the \u2018Condition\u2019 action to validate that the content type of the audio attachment must be in WAV format. Inside this set the value of the \u2018Body Content\u2019 variable using the content type and content of the current attachment audio file.<\/p>\n Expressions from the above image:<\/p>\n Add \u2018HTTP\u2019 action and do the following configurations,<\/p>\n Note:<\/u><\/strong> Make sure to use your region code at the highlighted in the URL.<\/p>\n Add a \u2018Parse JSON\u2019 action to get the text of the audio attachment.<\/p>\n Schema:<\/u><\/strong><\/p>\n Expressions from the above image:<\/p>\n Add the \u2018Append to string variable\u2019 step and append the audio file text along with the file name.<\/p>\n We can use the above output for further use.<\/p>\n By following these steps, you can effectively convert speech to text using Azure Speech Service in a Power Automate flow. <\/p>\n <\/p>\n <\/p>\n <\/p>\n <\/p>\n About Sam Kumar<\/strong><\/p>\n Sam Kumar is the Vice President of Marketing at Inogic, a Microsoft Gold ISV Partner renowned for its innovative apps for Dynamics 365 CRM and Power Apps. With a rich history in Dynamics 365 and Power Platform development, Sam leads a team of certified CRM developers dedicated to pioneering cutting-edge technologies with Copilot and Azure AI the latest additions. Passionate about transforming the CRM industry, Sam\u2019s insights and leadership drive Inogic\u2019s mission to change the \u201cDynamics\u201d of CRM.<\/p>\n More about\u00a0Sam Kumar<\/a><\/p>\n","protected":false},"excerpt":{"rendered":" Azure provides Speech Services that let developers add advanced speech features to achieve complex functionality, including Speech-to-Text. With Azure Speech Services, we can convert speech to text. \u00a0In this blog post, let us check how the conversion from speech to text using Azure Speech Service in a Power Automate flow is done. The following steps\u2026 Read More »<\/a><\/span><\/p>\n","protected":false},"author":11,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[1985],"tags":[2894,2542],"class_list":["post-38475","post","type-post","status-publish","format-standard","hentry","category-power-automate","tag-azure-speech-service","tag-power-automate-flow"],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts\/38475","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/users\/11"}],"replies":[{"embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/comments?post=38475"}],"version-history":[{"count":0,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/posts\/38475\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/media?parent=38475"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/categories?post=38475"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.inogic.com\/blog\/wp-json\/wp\/v2\/tags?post=38475"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Step 1: Create an \u2018Automated\u2019 flow<\/strong><\/h2>\n
![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-1.png\")
<\/p>\n![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-2.png\")
<\/p>\nStep 2: Initialize the String variable <\/strong><\/h2>\n
![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-3.png\")
<\/p>\nStep 3: Initialize the Object variable <\/strong><\/h2>\n
![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-4.png\")
<\/p>\nStep 4: Get Attachments<\/strong><\/h2>\n
\n
![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-5.png\")
<\/p>\nStep 5: Validate the content type of the audio attachment<\/strong><\/h2>\n
![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-6.png\")
<\/p>\n\n
Step 6: Convert Speech-To-Text<\/strong><\/h2>\n
\n
\n
\n
![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-7.png\")
<\/p>\nStep 7: Get the text of the audio attachment<\/strong><\/h2>\n
\r\n{\r\n \"type\": \"object\",\r\n \"properties\": {\r\n \"type\": {\r\n \"type\": \"string\"\r\n },\r\n \"properties\": {\r\n \"type\": \"object\",\r\n \"properties\": {\r\n \"RecognitionStatus\": {\r\n \"type\": \"object\",\r\n \"properties\": {\r\n \"type\": {\r\n \"type\": \"string\"\r\n }\r\n }\r\n },\r\n \"Offset\": {\r\n \"type\": \"object\",\r\n \"properties\": {\r\n \"type\": {\r\n \"type\": \"string\"\r\n }\r\n }\r\n },\r\n \"Duration\": {\r\n \"type\": \"object\",\r\n \"properties\": {\r\n \"type\": {\r\n \"type\": \"string\"\r\n }\r\n }\r\n },\r\n \"DisplayText\": {\r\n \"type\": \"object\",\r\n \"properties\": {\r\n \"type\": {\r\n \"type\": \"string\"\r\n }\r\n }\r\n }\r\n }\r\n }\r\n }\r\n}\r\n<\/pre>\n![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-8-e1719308769371.png\")
<\/p>\n![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-9.png\")
<\/p>\n\n
![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-10.png\")
<\/p>\nStep 8: Append audio text in the variable<\/strong><\/h2>\n
![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-11.png\")
<\/p>\n![\"Convert](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2024\/06\/Convert-speech-to-text-using-Azure-Speech-service-12.png\")
<\/p>\nConclusion:<\/strong><\/h2>\n
![\"Click2Export\"](\"https:\/\/www.inogic.com\/blog\/wp-content\/uploads\/2023\/04\/Click2Export.gif\")
<\/a><\/p>\n