AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-14 05:05:59 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat/application api add speech to text (#655)

Browse Source
This commit is contained in:
zxhlyh 2023-07-27 14:53:19 +08:00 committed by GitHub
parent 23e3413655
commit ae7c0380dc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 84 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
web/app/components/develop/template/template_chat.en.mdx
View File

@ -380,6 +380,48 @@ For versatile conversational apps using a Q&A format, call the chat-messages API
</Col>
</Row>
---
<Heading
url='/audio-to-text'
method='POST'
title='speech to text'
name='#audio'
/>
<Row>
<Col>
Speech to text, only supports openai model.
### Request Body
<Properties>
<Property name='file' type='file' key='file'>
Audio file.
File uploads are currently limited to 15 MB and the following input file types are supported: mp3, mp4, mpeg, mpga, m4a, wav, and webm.
</Property>
</Properties>
</Col>
<Col sticky>
<CodeGroup title="Request" tag="POST" label="/audio-to-text" targetCode={`curl --location --request POST '${props.appDetail.api_base_url}/audio-to-text' \\\n--header 'Authorization: Bearer ENTER-YOUR-SECRET-KEY' \\\n--form 'file=@localfile;type=audio/[mp3|mp4|mpeg|mpga|m4a|wav|webm]'`}>
```bash {{ title: 'cURL' }}
curl --location --request POST 'https://cloud.langgenius.dev/api/conversations/name' \
--header 'Authorization: Bearer ENTER-YOUR-SECRET-KEY' \
--form 'file=@localfile;type=audio/mp3'
```
</CodeGroup>
<CodeGroup title="Response">
```json {{ title: 'Response' }}
{
"text": ""
}
```
</CodeGroup>
</Col>
</Row>
---

42
web/app/components/develop/template/template_chat.zh.mdx
View File

@ -379,6 +379,48 @@ import { Row, Col, Properties, Property, Heading, SubProperty } from '../md.tsx'
</Col>
</Row>
---
<Heading
url='/audio-to-text'
method='POST'
title='语音转文字'
name='#audio'
/>
<Row>
<Col>
语音转文字，仅支持 openai 模型。
### Request Body
<Properties>
<Property name='file' type='file' key='file'>
语音文件。
文件上传当前限制为 15 MB，并且支持以下输入文件类型：mp3、mp4、mpeg、mpga、m4a、wav 和 webm。
</Property>
</Properties>
</Col>
<Col sticky>
<CodeGroup title="Request" tag="POST" label="/audio-to-text" targetCode={`curl --location --request POST '${props.appDetail.api_base_url}/audio-to-text' \\\n--header 'Authorization: Bearer ENTER-YOUR-SECRET-KEY' \\\n--form 'file=@localfile;type=audio/[mp3|mp4|mpeg|mpga|m4a|wav|webm]`}>
```bash {{ title: 'cURL' }}
curl --location --request POST 'https://cloud.langgenius.dev/api/conversations/name' \
--header 'Authorization: Bearer ENTER-YOUR-SECRET-KEY' \
--form 'file=@localfile;type=audio/mp3'
```
</CodeGroup>
<CodeGroup title="Response">
```json {{ title: 'Response' }}
{
"text": ""
}
```
</CodeGroup>
</Col>
</Row>
---