Merge branch 'ENDOC-298' of https://github.com/AgoraIO/Doc-Source-Pri…

…vate into staging

assets/images/real-time-stt/real-time-stt.puml

@@ -0,0 +1,24 @@
+@startuml
+
+participant "Your app server" as APP
+participant "Real-Time STT" as RTT
+
+group Start transcription
+APP -> RTT: 1 Call `acquire` to acquire a resource
+RTT -> APP: 2 Return the resource ID
+APP -> RTT: 3 Call `start` to start transcription
+RTT <- APP: 4 Get the task ID
+end
+
+group During transcription (Optional multiple calls)
+APP -> RTT: Call `query` to query task status
+RTT -> APP: Return current status
+APP -> RTT: Call `update` to update configuration
+end
+
+group Stop transcription
+APP -> RTT: Call `stop` to stop transcription
+RTT -> APP: Return task status
+end
+
+@enduml

real-time-stt/develop/_category_.json

@@ -0,0 +1,6 @@
+{
+  "position": 3,
+  "label": "Develop",
+  "collapsible": true,
+  "link": null
+}

real-time-stt/develop/api-callback-service.mdx

@@ -0,0 +1,13 @@
+---
+title: 'API callback service'
+sidebar_position: 7
+type: docs
+description: >
+  Receive notifications about Real-Time STT events
+---
+
+import CallbackService from '@docs/shared/real-time-stt/develop/callback-service.mdx';
+
+export const toc = [{}];
+
+<CallbackService PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />

real-time-stt/develop/enable-service.mdx

@@ -0,0 +1,13 @@
+---
+title: 'Best practice in enabling Real-Time STT on the client side'
+sidebar_position: 6
+type: docs
+description: >
+  Enable the Real-Time STT service
+---
+
+import EnableService from '@docs/shared/real-time-stt/develop/enable-service.mdx';
+
+export const toc = [{}];
+
+<EnableService PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />

real-time-stt/develop/encrypt-captions.mdx

@@ -0,0 +1,14 @@
+---
+title: 'Encrypt captions'
+sidebar_position: 1
+type: docs
+description: >
+  Encrypt the captions transcribed with RTT
+---
+
+import EncryptCaptions from '@docs/shared/real-time-stt/develop/encrypt-captions.mdx';
+
+export const toc = [{}];
+
+<EncryptCaptions PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />
+

real-time-stt/develop/record-captions.mdx

@@ -0,0 +1,14 @@
+---
+title: 'Record captions'
+sidebar_position: 2
+type: docs
+description: >
+  Record the captions transcribed with RTT in real time
+---
+
+import RecordCaptions from '@docs/shared/real-time-stt/develop/record-captions.mdx';
+
+export const toc = [{}];
+
+<RecordCaptions PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />
+

real-time-stt/develop/supported-languages.mdx

@@ -0,0 +1,14 @@
+---
+title: 'Supported languages'
+sidebar_position: 5
+type: docs
+description: >
+  The list of languages supported for real-time speech-to-text
+---
+
+import SupportedLanguages from '@docs/shared/real-time-stt/develop/supported-languages.mdx';
+
+export const toc = [{}];
+
+<SupportedLanguages PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />
+

real-time-stt/develop/transcribe-individual-host.mdx

@@ -0,0 +1,14 @@
+---
+title: 'Transcribe specified hosts'
+sidebar_position: 3
+type: docs
+description: >
+  Transcribe the speech of specific channel hosts only
+---
+
+import TranscribeHost from '@docs/shared/real-time-stt/develop/transcribe-individual-host.mdx';
+
+export const toc = [{}];
+
+<TranscribeHost PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />
+

real-time-stt/develop/update-service.mdx

@@ -0,0 +1,13 @@
+---
+title: 'Update service'
+sidebar_position: 8
+type: docs
+description: >
+  Update the Real-Time STT service
+---
+
+import UpdateService from '@docs/shared/real-time-stt/develop/update-service.mdx';
+
+export const toc = [{}];
+
+<UpdateService PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />

real-time-stt/get-started/_category_.json

@@ -0,0 +1,6 @@
+{
+  "position": 2,
+  "label": "Get started",
+  "collapsible": true,
+  "link": null
+}

real-time-stt/get-started/quickstart.mdx

@@ -0,0 +1,15 @@
+---
+title: 'REST quickstart'
+sidebar_position: 1
+type: docs
+platform_selector: false
+description: >
+  Transcribe audio content of a host's media stream into written words in real time.
+---
+
+import RealTimeSTT from '@docs/shared/real-time-stt/get-started/quickstart.mdx';
+
+export const toc = [{}];
+
+<RealTimeSTT PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />
+

real-time-stt/overview/_category_.json

@@ -0,0 +1,6 @@
+{
+  "position": 1,
+  "label": "Overview",
+  "collapsible": true,
+  "link": null
+}

real-time-stt/overview/core-concepts.mdx

@@ -0,0 +1,15 @@
+---
+title: 'Core concepts'
+sidebar_position: 2
+type: docs
+platform_selector: false
+description: >
+  Ideas that are central to developing with Agora.
+---
+
+import CoreConcepts from '@docs/shared/common/core-concepts/real-time-stt.mdx';
+
+export const toc = [{}];
+
+<CoreConcepts PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />
+

real-time-stt/overview/pricing.mdx

@@ -0,0 +1,61 @@
+---
+title: 'Pricing'
+sidebar_position: 3
+type: docs
+platform_selector: false
+description: >
+  Introduces the billing policy for Real-Time STT.
+---
+
+export const toc = [{}];
+
+This page introduces the billing policy for the <Vpd k="NAME"/> add-on provided by Agora.
+
+Your billing details may differ if you have signed a contract with Agora.
+
+## Overview
+
+Agora calculates the billing of all projects under your Agora account on a monthly basis. Billing begins once you
+enable <Vpd k="NAME"/>.
+
+## Transcription fee
+
+When <Vpd k="NAME"/> is enabled for a channel, it transcribes the audio of its active hosts. When <Vpd k="NAME"/> is enabled for specific hosts, it only transcribes the audio of the specified hosts and ignores the others. The <Vpd k="NAME"/> service employs algorithms that remove the periods of silence and improve WER (Word Error Rate) of transcription. The processed audio is transcribed by the <Vpd k="NAME"/> engine and referred to as transcription duration. Agora charges for the transcription duration of all or specified hosts in the channel.
+
+The unit price is as follows:
+
+|Billing item |Usage, minutes per month |Pricing, US$/1,000 minutes|
+|-------------|--------------------|--------------------------|
+|Transcription duration|Above 0         | 16.99                     |
+
+Examples:
+- Let's say there is a channel existing for 10 minutes. There are 3 active hosts - A, B, and C - all in the unmuted state.
+- #1: If <Vpd k="NAME"/> is enabled for this channel, the algorithm will remove 8 minutes of silent audio for host A, 7 minutes for host B, and 7 minutes for host C. Therefore, the transcription duration is (10 - 8) + (10 -7) + (10 - 7) = 2 + 3 + 3 = 8 minutes.
+- #2: If <Vpd k="NAME"/> is enabled for host A, the algorithm will remove 8 minutes of silent audio for host A. The transcription duration is 10 - 8 = 2 minutes.
+
+Notes:
+- WER is known as the accuracy of an STT engine - the smaller, the better.
+- Enabling <Vpd k="NAME"/> for a channel or host that are quiet for a long time is not recommended. In this case, audio is processed and removed, and the STT engine runs in the standby mode. Agora will charge for this standby duration at $0.99/1,000 minutes. In example #1, the standby duration is calculated the following way: Enable duration - transcription duration = 10 - 8 = 2 minutes. In example #2, the standby duration is calculated the following way: Enable duration - transcription duration = 10 - 2 = 8 minutes.
+
+## Language identification fee
+
+<Vpd k="NAME"/> supports dynamic language detection when two or more languages are enabled for a channel or specific hosts. The LID (language identification) duration is the same as the transcription duration.
+
+|Billing item|Usage, minutes per month |Pricing, US$/1,000 minutes|
+|--------------------|--------------------|--------------------------|
+|Language identification duration|Above 0         | 5.00                     |
+
+Examples:
+- Let's say there is a channel existing for 10 minutes. There are 3 active hosts - A, B, and C - all in the unmuted state.
+- #3: If Spanish and Chinese LID is enabled for this channel, the algorithm will remove 8 minutes of silent audio for host A, 7 minutes for host B and 7 minutes for host C. Therefore, the transcription duration is 2 + 3 + 3 = 8 minutes. the LID duration is 8 minutes, too, being the sum of 2 minutes for host A, 3 minutes for host B, and 3 minutes for host C.
+- If Spanish and Chinese LID is enabled for host A, then the transcription duration and LID duration are both 2 minutes.
+
+Notes:
+- The <Vpd k="NAME"/> transcription duration does not change if you enable more than 1 language.
+- If only 1 language is set for a channel or a specified host, the language detection will not start.
+
+## Free-of-charge duration
+
+<Vpd k="NAME"/> provides 300 minutes of free-of-charge duration for integration and testing purposes.
+
+Contact [email protected] or your AE to get a discount.

real-time-stt/overview/product-overview.mdx

@@ -0,0 +1,53 @@
+---
+title: 'Product overview'
+sidebar_position: 1
+platform_selector: false
+description: >
+  Create a better user experience with the most accurate live transcription and subtitling.
+---
+
+
+<ProductOverview
+    title="Real-Time Speech-To-Text"
+    img="/images/real-time-stt/real-time-stt.png"
+    apiQuickStartLink="/real-time-stt/get-started"
+    apiReferenceLink="/api-reference"
+    samplesLink="https://github.com/AgoraIO/agora-rtt-server"
+    productFeatures={[
+        {
+            title: "Live transcription for RTC",
+            content: "Integrated with Agora’s voice and video service, live transcription and captions improve accessibility for your audience. Perfect for meetings, live streaming, lectures, interviews, live shopping, and more.",
+            link: ""
+        },
+        {
+            title: "Cloud-based STT",
+            content: "Cloud-based service converts voice to text based on the active or specific hosts, then distributes the text to all participants in the channel for further processing. Does not depend on the performance of the client device and network.",
+            link: ""
+        },
+        {
+            title: "Speaker labeling",
+            content: "Label each transcribed text with the speaker's UID. Separate transcription of each host ensures accuracy even when multiple hosts are talking simultaneously.",
+            link: ""
+        },
+        {
+            title: "Caption recording",
+            content: "Upload the transcriptions as .vtt files to cloud storage, then play back audio or video recordings with closed captions (CC). The timestamp in the .vtt file allows to start playback from the point when the text was generated. ",
+            link: ""
+        },
+        {
+            title: "Multi-language support",
+            content: "Real-time transcription supports all major languages and dialects, and each channel can support audio to text transcription for up to two languages simultaneously.",
+            link: ""
+        },
+        {
+            title: "Enterprise-grade security and compliance",
+            content: "Agora is ISO and SOC 2 certified and meets compliance standards for regional privacy laws and industry regulations, including GDPR, CCPA, and HIPAA. Live captions and transcription can be encrypted the same way as the RTC audio or video.  ",
+            link: ""
+        },
+    ]}
+
+>
+
+Agora Real-Time Speech-To-Text (STT) enables you to transcribe audio of each host to provide live closed captions (CC) and transcription for improved accessibility. Real-Time STT also removes silent audio to improve transcription performance and reduce cost. The output text can be processed for LLM (for example, GPT). Real-Time STT is the first step in letting Real-Time Engagement enter the AI area.
+
+</ProductOverview>

real-time-stt/reference/_category_.json

@@ -0,0 +1,6 @@
+{
+  "position": 4,
+  "label": "Reference",
+  "collapsible": true,
+  "link": null
+}

real-time-stt/reference/common-errors.mdx

@@ -0,0 +1,13 @@
+---
+title: 'Common errors'
+sidebar_position: 9
+type: docs
+description: >
+  Common errors
+---
+
+import CommonErrors from '@docs/shared/real-time-stt/reference/common-errors.mdx';
+
+export const toc = [{}];
+
+<CommonErrors PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app" />

real-time-stt/reference/firewall.mdx

@@ -0,0 +1,14 @@
+---
+title: 'Firewall requirements'
+sidebar_position: 4
+type: docs
+platform_selector: false
+description: >
+  use Agora products in environments with restricted network access
+---
+
+import Firewall from '@docs/shared/common/_firewall.mdx';
+
+export const toc = [{}];
+
+<Firewall PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app"  />

real-time-stt/reference/glossary.mdx

@@ -0,0 +1,14 @@
+---
+title: 'Glossary'
+sidebar_position: 5
+type: docs
+platform_selector: false
+description: >
+  A list of terms used in Agora documentation.
+---
+
+import Glossary from '@docs/shared/common/_glossary.mdx';
+
+export const toc = [{}];
+
+<Glossary PRODUCT="Real-Time STT" company="Agora" PATH="real-time-stt" client="app"  />

real-time-stt/reference/manage-agora-account.mdx

@@ -0,0 +1,14 @@
+---
+title: 'Agora account management'
+sidebar_position: 2
+type: docs
+platform_selector: false
+description: >
+  Create, manage and update your Agora account.
+---
+
+import ManageAccount from '@docs/shared/common/_manage-agora-account.mdx';
+
+export const toc = [{}];
+
+<ManageAccount PRODUCT="Real-Time STT" company="Agora" client="app" PATH="real-time-stt" />