Added audio and video transcription for chats and assistants (#856)

app/MindWork AI Studio/Assistants/AssistantBase.razor

@@ -31,14 +31,16 @@
 
                 @if (this.Body is not null)
                 {
-                    <CascadingValue Value="@this">
-                        <CascadingValue Value="@this.Component">
-                            @this.Body
+                    <CascadingValue Value="@this.CurrentMediaImportOwner">
+                        <CascadingValue Value="@this">
+                            <CascadingValue Value="@this.Component">
+                                @this.Body
+                            </CascadingValue>
                         </CascadingValue>
                     </CascadingValue>
                     
                     <MudStack Row="true" AlignItems="AlignItems.Center" StretchItems="StretchItems.Start" Class="mb-3">
-                        <MudButton Disabled="@(this.SubmitDisabled || this.IsProcessing)" Variant="Variant.Filled" OnClick="@(async () => await this.Start())" Style="@this.SubmitButtonStyle">
+                        <MudButton Disabled="@(this.SubmitDisabled || this.IsProcessing || this.MediaTranscriptionService.IsBusy(this.CurrentMediaImportOwner))" Variant="Variant.Filled" OnClick="@(async () => await this.Start())" Style="@this.SubmitButtonStyle">
                             @this.SubmitText
                         </MudButton>
                         @if (this.IsProcessing)
@@ -158,7 +160,7 @@
 
                 @if (this.ShowReset)
                 {
-                    <MudButton Variant="Variant.Filled" Style="@this.GetResetColor()" StartIcon="@Icons.Material.Filled.Refresh" OnClick="@(async () => await this.InnerResetForm())">
+                    <MudButton Variant="Variant.Filled" Style="@this.GetResetColor()" StartIcon="@Icons.Material.Filled.Refresh" Disabled="@this.MediaTranscriptionService.IsBusy(this.CurrentMediaImportOwner)" OnClick="@(async () => await this.InnerResetForm())">
                         @TB("Reset")
                     </MudButton>
                 }

app/MindWork AI Studio/Assistants/AssistantBase.razor.cs

@@ -4,6 +4,7 @@ using AIStudio.Settings;
 using AIStudio.Dialogs.Settings;
 using AIStudio.Tools.AIJobs;
 using AIStudio.Tools.AssistantSessions;
+using AIStudio.Tools.Media;
 using AIStudio.Tools.Services;
 
 using Microsoft.AspNetCore.Components;
@@ -47,6 +48,9 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
     /// </summary>
     [Inject]
     protected AIJobService AIJobService { get; init; } = null!;
+
+    [Inject]
+    protected MediaTranscriptionService MediaTranscriptionService { get; init; } = null!;
     
     protected abstract string Title { get; }
     
@@ -132,6 +136,7 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
     protected CancellationTokenSource? CancellationTokenSource;
     private bool isDisposed;
     private AssistantSessionKey assistantSessionKey;
+    private MediaImportOwner CurrentMediaImportOwner => MediaImportOwner.ForAssistant(this.assistantSessionKey);
     private Guid? assistantSessionId;
     private AssistantSessionSnapshot? pendingRenderedAssistantSessionSnapshot;
 
@@ -145,6 +150,9 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
     /// </summary>
     protected bool HasAssistantSession => this.assistantSessionId is not null;
 
+    /// <summary>Gets whether this assistant currently owns active media work.</summary>
+    protected bool IsMediaImportBusy => this.MediaTranscriptionService.IsBusy(this.CurrentMediaImportOwner);
+
     /// <summary>
     /// Gets the assistant-specific identifier used to distinguish session slots.
     /// </summary>
@@ -154,6 +162,7 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
 
     protected override async Task OnInitializedAsync()
     {
+        this.MediaTranscriptionService.StateChanged += this.OnMediaImportStateChanged;
         await base.OnInitializedAsync();
 
         if (!this.SettingsManager.IsAssistantVisible(this.Component, assistantName: this.Title))
@@ -176,6 +185,7 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
         this.CurrentChatTemplate = this.SettingsManager.GetPreselectedChatTemplate(this.Component);
         this.assistantSessionKey = new(this.Component, this.AssistantSessionInstanceId);
         await this.AttachAssistantSessionIfAvailable();
+        await this.ConsumeMediaOutcomeAsync();
     }
 
     protected override async Task OnParametersSetAsync()
@@ -223,6 +233,9 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
 
     private async Task Start()
     {
+        if (this.MediaTranscriptionService.IsBusy(this.CurrentMediaImportOwner))
+            return;
+
         var activeSession = this.AssistantSessionService.TryGetSnapshot(this.assistantSessionKey);
         if (activeSession?.IsActive ?? false)
         {
@@ -634,10 +647,12 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
     
     private async Task InnerResetForm()
     {
-        if (this.AssistantSessionService.TryGetSnapshot(this.assistantSessionKey)?.IsActive ?? false)
+        if ((this.AssistantSessionService.TryGetSnapshot(this.assistantSessionKey)?.IsActive ?? false)
+            || this.MediaTranscriptionService.IsBusy(this.CurrentMediaImportOwner))
             return;
 
         await this.AssistantSessionService.ClearAsync(this.assistantSessionKey);
+        this.MediaTranscriptionService.ClearOwnerState(this.CurrentMediaImportOwner);
         this.assistantSessionId = null;
         this.ResultingContentBlock = null;
         this.ProviderSettings = Settings.Provider.NONE;
@@ -672,6 +687,7 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
 
     protected override void DisposeResources()
     {
+        this.MediaTranscriptionService.StateChanged -= this.OnMediaImportStateChanged;
         this.isDisposed = true;
         try
         {
@@ -686,6 +702,46 @@ public abstract partial class AssistantBase<TSettings> : AssistantLowerBase wher
         base.DisposeResources();
     }
 
+    /// <summary>Refreshes assistant actions when the shared import lane changes.</summary>
+    private void OnMediaImportStateChanged(MediaImportOwner owner)
+    {
+        if (owner == this.CurrentMediaImportOwner)
+            _ = this.InvokeAsync(async () =>
+            {
+                await this.ConsumeMediaOutcomeAsync();
+                this.StateHasChanged();
+            });
+    }
+
+    /// <summary>Consumes a terminal media notification when this assistant is visible.</summary>
+    private async Task ConsumeMediaOutcomeAsync()
+    {
+        var outcome = this.MediaTranscriptionService.TryConsumeOutcome(this.CurrentMediaImportOwner);
+        if (outcome is null)
+            return;
+
+        if (outcome.Failures.Count > 0)
+        {
+            var message = string.Join(Environment.NewLine, outcome.Failures.Select(failure => $"{failure.FileName}: {failure.UserMessage}"));
+            await this.MessageBus.SendError(new(Icons.Material.Filled.VoiceChat, message));
+        }
+        else if (outcome.Status is MediaImportStatus.FAILED)
+        {
+            await this.MessageBus.SendError(new(Icons.Material.Filled.VoiceChat, this.TB("The media file could not be transcribed.")));
+        }
+
+        if (outcome.Warnings.Count > 0)
+        {
+            var message = string.Join(Environment.NewLine, outcome.Warnings.Select(warning => $"{warning.FileName}: {warning.UserMessage}"));
+            await this.MessageBus.SendWarning(new(Icons.Material.Filled.VoiceChat, message));
+        }
+
+        if (outcome.Status is MediaImportStatus.CANCELLED)
+        {
+            await this.MessageBus.SendWarning(new(Icons.Material.Filled.VoiceChat, this.TB("The media transcription was canceled.")));
+        }
+    }
+
     #endregion
 
     #region Assistant sessions

app/MindWork AI Studio/Assistants/DocumentAnalysis/DocumentAnalysisAssistant.razor

@@ -21,7 +21,7 @@
 }
 else
 {
-    <MudList Color="Color.Primary" T="DataDocumentAnalysisPolicy" Class="mb-1" SelectedValue="@this.selectedPolicy" SelectedValueChanged="@this.SelectedPolicyChanged">
+    <MudList Disabled="@this.ArePolicyControlsDisabled" Color="Color.Primary" T="DataDocumentAnalysisPolicy" Class="mb-1" SelectedValue="@this.selectedPolicy" SelectedValueChanged="@this.SelectedPolicyChanged">
         @foreach (var policy in this.SettingsManager.ConfigurationData.DocumentAnalysis.Policies)
         {
             @if (policy.IsEnterpriseConfiguration)
@@ -44,10 +44,10 @@ else
 }
 
 <MudStack Row="@true" Class="mt-1">
-    <MudButton OnClick="@this.AddPolicy" Variant="Variant.Filled" Color="Color.Primary">
+    <MudButton OnClick="@this.AddPolicy" Disabled="@this.ArePolicyControlsDisabled" Variant="Variant.Filled" Color="Color.Primary">
         @T("Add policy")
     </MudButton>
-    <MudButton OnClick="@this.RemovePolicy" Disabled="@((this.selectedPolicy?.IsProtected ?? true) || (this.selectedPolicy?.IsEnterpriseConfiguration ?? true))" Variant="Variant.Filled" Color="Color.Error">
+    <MudButton OnClick="@this.RemovePolicy" Disabled="@(this.ArePolicyControlsDisabled || (this.selectedPolicy?.IsProtected ?? true) || (this.selectedPolicy?.IsEnterpriseConfiguration ?? true))" Variant="Variant.Filled" Color="Color.Error">
         @T("Delete this policy")
     </MudButton>
 </MudStack>

app/MindWork AI Studio/Assistants/DocumentAnalysis/DocumentAnalysisAssistant.razor.cs

@@ -333,9 +333,14 @@ public partial class DocumentAnalysisAssistant : AssistantBaseCore<NoSettingsPan
     private bool IsNoPolicySelectedOrProtected => this.selectedPolicy is null || this.selectedPolicy.IsProtected;
     
     private bool IsNoPolicySelected => this.selectedPolicy is null;
+
+    private bool ArePolicyControlsDisabled => this.IsProcessing || this.IsMediaImportBusy;
     
     private void SelectedPolicyChanged(DataDocumentAnalysisPolicy? policy)
     {
+        if (this.ArePolicyControlsDisabled)
+            return;
+
         this.selectedPolicy = policy;
         this.ResetForm();
         this.policyDefinitionExpanded = !this.selectedPolicy?.IsProtected ?? true;
@@ -353,6 +358,9 @@ public partial class DocumentAnalysisAssistant : AssistantBaseCore<NoSettingsPan
     
     private async Task AddPolicy()
     {
+        if (this.ArePolicyControlsDisabled)
+            return;
+
         this.SettingsManager.ConfigurationData.DocumentAnalysis.Policies.Add(new ()
         {
             Id = Guid.NewGuid().ToString(),
@@ -373,6 +381,9 @@ public partial class DocumentAnalysisAssistant : AssistantBaseCore<NoSettingsPan
 
     private async Task RemovePolicy()
     {
+        if (this.ArePolicyControlsDisabled)
+            return;
+
         if(this.selectedPolicy is null)
             return;
         

app/MindWork AI Studio/Assistants/Dynamic/AssistantDynamic.razor

@@ -134,7 +134,7 @@ else
                 {
                     var fileState = this.assistantState.FileContent[fileContent.Name];
                     <div class="@fileContent.Class" style="@GetOptionalStyle(fileContent.Style)">
-                        <ReadFileContent @bind-FileContent="@fileState.Content" EnableDragDrop="true" Layer="@DropLayers.ASSISTANTS" CatchAllDocuments="true" />
+                        <ReadFileContent @bind-FileContent="@fileState.Content" MediaImportTargetId="@fileContent.Name" EnableDragDrop="true" Layer="@DropLayers.ASSISTANTS" CatchAllDocuments="true" />
                     </div>
                 }
                 break;

app/MindWork AI Studio/Assistants/I18N/allTexts.lua

@@ -304,6 +304,9 @@ UI_TEXT_CONTENT["AISTUDIO::ASSISTANTS::AGENDA::NUMBERPARTICIPANTSEXTENSIONS::T81
 -- Stop generation
 UI_TEXT_CONTENT["AISTUDIO::ASSISTANTS::ASSISTANTBASE::T1317408357"] = "Stop generation"
 
+-- The media file could not be transcribed.
+UI_TEXT_CONTENT["AISTUDIO::ASSISTANTS::ASSISTANTBASE::T1543974632"] = "The media file could not be transcribed."
+
 -- Reset
 UI_TEXT_CONTENT["AISTUDIO::ASSISTANTS::ASSISTANTBASE::T180921696"] = "Reset"
 
@@ -313,6 +316,9 @@ UI_TEXT_CONTENT["AISTUDIO::ASSISTANTS::ASSISTANTBASE::T1809312323"] = "Please se
 -- The assistant failed. The message is: '{0}'
 UI_TEXT_CONTENT["AISTUDIO::ASSISTANTS::ASSISTANTBASE::T1833836281"] = "The assistant failed. The message is: '{0}'"
 
+-- The media transcription was canceled.
+UI_TEXT_CONTENT["AISTUDIO::ASSISTANTS::ASSISTANTBASE::T241403726"] = "The media transcription was canceled."
+
 -- This assistant is already running. AI Studio opens the running session instead.
 UI_TEXT_CONTENT["AISTUDIO::ASSISTANTS::ASSISTANTBASE::T2575715765"] = "This assistant is already running. AI Studio opens the running session instead."
 
@@ -2293,9 +2299,24 @@ UI_TEXT_CONTENT["AISTUDIO::CHAT::IIMAGESOURCEEXTENSIONS::T349928509"] = "The ima
 -- Open Settings
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ASSISTANTBLOCK::T1172211894"] = "Open Settings"
 
+-- Media transcription was canceled. Open the assistant to review it.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ASSISTANTBLOCK::T1233815302"] = "Media transcription was canceled. Open the assistant to review it."
+
+-- Media transcription failed. Open the assistant to review it.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ASSISTANTBLOCK::T2177964639"] = "Media transcription failed. Open the assistant to review it."
+
+-- Media transcription completed with a warning. Open the assistant to review it.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ASSISTANTBLOCK::T2217674098"] = "Media transcription completed with a warning. Open the assistant to review it."
+
+-- Media is still being prepared.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ASSISTANTBLOCK::T2600900617"] = "Media is still being prepared."
+
 -- Assistant is still running.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ASSISTANTBLOCK::T2719896610"] = "Assistant is still running."
 
+-- The media transcript is ready.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ASSISTANTBLOCK::T3248321953"] = "The media transcript is ready."
+
 -- Assistant was canceled. Open it to review the result.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ASSISTANTBLOCK::T3390934621"] = "Assistant was canceled. Open it to review the result."
 
@@ -2398,18 +2419,33 @@ UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T1358313858"] = "Click t
 -- Drop files here to attach them.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T143112277"] = "Drop files here to attach them."
 
+-- The media file could not be transcribed.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T1543974632"] = "The media file could not be transcribed."
+
 -- Click here to attach files.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T1875575968"] = "Click here to attach files."
 
+-- Transcribe media files
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T2178031033"] = "Transcribe media files"
+
 -- Drag and drop files into the marked area or click here to attach documents:
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T230755331"] = "Drag and drop files into the marked area or click here to attach documents:"
 
+-- The media transcription was canceled.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T241403726"] = "The media transcription was canceled."
+
 -- Select files to attach
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T2495931372"] = "Select files to attach"
 
 -- Document Preview
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T285154968"] = "Document Preview"
 
+-- Media files require a configured transcription provider. Configure one in the transcription settings.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T3172443094"] = "Media files require a configured transcription provider. Configure one in the transcription settings."
+
+-- The selected audio and video files will be prepared locally. Their audio will then be uploaded to the configured transcription provider.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T322693339"] = "The selected audio and video files will be prepared locally. Their audio will then be uploaded to the configured transcription provider."
+
 -- Clear file list
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::ATTACHDOCUMENTS::T3759696136"] = "Clear file list"
 
@@ -2434,6 +2470,9 @@ UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::CHATCOMPONENT::T1317408357"] = "Stop gene
 -- Save chat
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::CHATCOMPONENT::T1516264254"] = "Save chat"
 
+-- The media file could not be transcribed.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::CHATCOMPONENT::T1543974632"] = "The media file could not be transcribed."
+
 -- Type your input here...
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::CHATCOMPONENT::T1849313532"] = "Type your input here..."
 
@@ -2446,6 +2485,9 @@ UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::CHATCOMPONENT::T2036185364"] = "Code"
 -- Italic
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::CHATCOMPONENT::T2377171085"] = "Italic"
 
+-- The media transcription was canceled.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::CHATCOMPONENT::T241403726"] = "The media transcription was canceled."
+
 -- Profile usage is disabled according to your chat template settings.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::CHATCOMPONENT::T2670286472"] = "Profile usage is disabled according to your chat template settings."
 
@@ -2671,6 +2713,24 @@ UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MANDATORYINFODISPLAY::T3511160492"] = "Ac
 -- Please review this text again. The content was changed.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MANDATORYINFODISPLAY::T941885055"] = "Please review this text again. The content was changed."
 
+-- Waiting to prepare media
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MEDIATRANSCRIPTIONSTATUS::T1167267986"] = "Waiting to prepare media"
+
+-- Stop media transcription
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MEDIATRANSCRIPTIONSTATUS::T1868377405"] = "Stop media transcription"
+
+-- Stopping media transcription
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MEDIATRANSCRIPTIONSTATUS::T1878101489"] = "Stopping media transcription"
+
+-- Inspecting media
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MEDIATRANSCRIPTIONSTATUS::T2431421733"] = "Inspecting media"
+
+-- Transcribing
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MEDIATRANSCRIPTIONSTATUS::T2938661425"] = "Transcribing"
+
+-- Preparing audio
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MEDIATRANSCRIPTIONSTATUS::T3200155905"] = "Preparing audio"
+
 -- Given that my employer's workplace uses both Windows and Linux, I wanted a cross-platform solution that would work seamlessly across all major operating systems, including macOS. Additionally, I wanted to demonstrate that it is possible to create modern, efficient, cross-platform applications without resorting to Electron bloatware. The combination of .NET and Rust with Tauri proved to be an excellent technology stack for building such robust applications.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::MOTIVATION::T1057189794"] = "Given that my employer's workplace uses both Windows and Linux, I wanted a cross-platform solution that would work seamlessly across all major operating systems, including macOS. Additionally, I wanted to demonstrate that it is possible to create modern, efficient, cross-platform applications without resorting to Electron bloatware. The combination of .NET and Rust with Tauri proved to be an excellent technology stack for building such robust applications."
 
@@ -2788,18 +2848,33 @@ UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::PROVIDERSELECTION::T4279448758"] = "Uses
 -- Provider
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::PROVIDERSELECTION::T900237532"] = "Provider"
 
+-- The media file could not be transcribed.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T1543974632"] = "The media file could not be transcribed."
+
 -- Failed to load file content
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T1989554334"] = "Failed to load file content"
 
 -- Drop one file here to load its content.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T2274562398"] = "Drop one file here to load its content."
 
+-- The media transcription was canceled.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T241403726"] = "The media transcription was canceled."
+
+-- The selected media file will be prepared locally. Its audio will then be uploaded to the configured transcription provider.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T2839709466"] = "The selected media file will be prepared locally. Its audio will then be uploaded to the configured transcription provider."
+
+-- Media files require a configured transcription provider. Configure one in the transcription settings.
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T3172443094"] = "Media files require a configured transcription provider. Configure one in the transcription settings."
+
 -- Use file content as input
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T3499386973"] = "Use file content as input"
 
 -- Select file to read its content
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T354817589"] = "Select file to read its content"
 
+-- Transcribe media file
+UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READFILECONTENT::T3554222960"] = "Transcribe media file"
+
 -- The content is cleaned using an LLM agent: the main content is extracted, advertisements and other irrelevant things are attempted to be removed; relative links are attempted to be converted into absolute links so that they can be used.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::READWEBCONTENT::T1164201762"] = "The content is cleaned using an LLM agent: the main content is extracted, advertisements and other irrelevant things are attempted to be removed; relative links are attempted to be converted into absolute links so that they can be used."
 
@@ -3538,9 +3613,6 @@ UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VISION::T586430036"] = "Useful assistants
 -- Voice recording has been disabled for this session because audio playback could not be initialized on the client.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T1123032432"] = "Voice recording has been disabled for this session because audio playback could not be initialized on the client."
 
--- Failed to create the transcription provider.
-UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T1689988905"] = "Failed to create the transcription provider."
-
 -- Failed to start audio recording.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T2144994226"] = "Failed to start audio recording."
 
@@ -3559,21 +3631,12 @@ UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T2851219233"] = "Transcrip
 -- Unfortunately, there was an error communicating with the AI system.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T3236134591"] = "Unfortunately, there was an error communicating with the AI system."
 
--- The configured transcription provider was not found.
-UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T331613105"] = "The configured transcription provider was not found."
-
 -- Failed to stop audio recording.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T3462568264"] = "Failed to stop audio recording."
 
--- The configured transcription provider does not meet the minimum confidence level.
-UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T3834149033"] = "The configured transcription provider does not meet the minimum confidence level."
-
 -- An error occurred during transcription.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T588743762"] = "An error occurred during transcription."
 
--- No transcription provider is configured.
-UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T663630295"] = "No transcription provider is configured."
-
 -- The transcription result is empty.
 UI_TEXT_CONTENT["AISTUDIO::COMPONENTS::VOICERECORDER::T974954792"] = "The transcription result is empty."
 
@@ -6748,9 +6811,6 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2037899437"] = "Copies the serve
 -- This library is used to create temporary folders in runtime tests and supporting filesystem operations.
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2160280545"] = "This library is used to create temporary folders in runtime tests and supporting filesystem operations."
 
--- This library is used to determine the file type of a file. This is necessary, e.g., when we want to stream a file.
-UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2173617769"] = "This library is used to determine the file type of a file. This is necessary, e.g., when we want to stream a file."
-
 -- For the secure communication between the user interface and the runtime, we need to create certificates. This Rust library is great for this purpose.
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2174764529"] = "For the secure communication between the user interface and the runtime, we need to create certificates. This Rust library is great for this purpose."
 
@@ -6769,6 +6829,9 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2301484629"] = "Configuration pl
 -- The C# language is used for the implementation of the user interface and the backend. To implement the user interface with C#, the Blazor technology from ASP.NET Core is used. All these technologies are integrated into the .NET SDK.
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2329884315"] = "The C# language is used for the implementation of the user interface and the backend. To implement the user interface with C#, the Blazor technology from ASP.NET Core is used. All these technologies are integrated into the .NET SDK."
 
+-- We use Rubato to resample the decoded audio to 48 kHz before the Opus encoding.
+UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2345444286"] = "We use Rubato to resample the decoded audio to 48 kHz before the Opus encoding."
+
 -- Linux AppImages bundle GStreamer components to support microphone access and WebM audio recording in the embedded WebKitGTK web view.
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T234598990"] = "Linux AppImages bundle GStreamer components to support microphone access and WebM audio recording in the embedded WebKitGTK web view."
 
@@ -6850,6 +6913,9 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2929232062"] = "Copies the confi
 -- Copies the root certificate fingerprint to the clipboard
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T2989678330"] = "Copies the root certificate fingerprint to the clipboard"
 
+-- This library identifies files by their content. It is used for document streaming and as the first safety and media classification step before local audio processing.
+UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3002755581"] = "This library identifies files by their content. It is used for document streaming and as the first safety and media classification step before local audio processing."
+
 -- Changelog
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3017574265"] = "Changelog"
 
@@ -6895,6 +6961,9 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3315279770"] = "External HTTPS c
 -- User-language provided by the OS
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3334355246"] = "User-language provided by the OS"
 
+-- webm-iterable provides the EBML and WebM writing path for normalized audio.
+UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3385332793"] = "webm-iterable provides the EBML and WebM writing path for normalized audio."
+
 -- Status:
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3396815215"] = "Status:"
 
@@ -6955,6 +7024,9 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T396609403"] = "not applicable"
 -- Copies the allowed host configuration to the clipboard
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3970230163"] = "Copies the allowed host configuration to the clipboard"
 
+-- Symphonia is used for media container demuxing and audio decoding. The exact MPL-covered source is available from the repository linked and is identified in the offline notices bundled with AI Studio.
+UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3971563979"] = "Symphonia is used for media container demuxing and audio decoding. The exact MPL-covered source is available from the repository linked and is identified in the offline notices bundled with AI Studio."
+
 -- Installed Pandoc version
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T3983971016"] = "Installed Pandoc version"
 
@@ -6973,6 +7045,9 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T4060906280"] = "This library is
 -- This library is used to create asynchronous streams in Rust. It allows us to work with streams of data that can be produced asynchronously, making it easier to handle events or data that arrive over time. We use this, e.g., to stream arbitrary data from the file system to the embedding system.
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T4079152443"] = "This library is used to create asynchronous streams in Rust. It allows us to work with streams of data that can be produced asynchronously, making it easier to handle events or data that arrive over time. We use this, e.g., to stream arbitrary data from the file system to the embedding system."
 
+-- Ropus provides the Opus encoder and decoder used by the media pipeline.
+UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T4113556626"] = "Ropus provides the Opus encoder and decoder used by the media pipeline."
+
 -- Community & Code
 UI_TEXT_CONTENT["AISTUDIO::PAGES::INFORMATION::T4158546761"] = "Community & Code"
 
@@ -8485,6 +8560,42 @@ UI_TEXT_CONTENT["AISTUDIO::TOOLS::RUST::FILETYPES::T378481461"] = "Source like p
 -- Document
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::RUST::FILETYPES::T4165204724"] = "Document"
 
+-- The configured transcription provider could not be created.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T1235984176"] = "The configured transcription provider could not be created."
+
+-- The selected media file no longer exists.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T129859547"] = "The selected media file no longer exists."
+
+-- The selected media file does not contain an audio track.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T134825479"] = "The selected media file does not contain an audio track."
+
+-- The media file could not be transcribed.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T1543974632"] = "The media file could not be transcribed."
+
+-- The selected file cannot be processed as media.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T1707342767"] = "The selected file cannot be processed as media."
+
+-- The audio track contains no audible signal, so there is nothing to transcribe.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T1988190152"] = "The audio track contains no audible signal, so there is nothing to transcribe."
+
+-- The media file is damaged or its format could not be identified.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T2004316549"] = "The media file is damaged or its format could not be identified."
+
+-- This media format or audio codec is not supported.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T2142564510"] = "This media format or audio codec is not supported."
+
+-- No usable transcription provider is configured.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T2282521655"] = "No usable transcription provider is configured."
+
+-- The media file could not be prepared for transcription.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T2749117459"] = "The media file could not be prepared for transcription."
+
+-- The transcription provider could not transcribe the media file.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T3091669215"] = "The transcription provider could not transcribe the media file."
+
+-- The media pipeline ended without an output file.
+UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::MEDIATRANSCRIPTIONSERVICE::T632852430"] = "The media pipeline ended without an output file."
+
 -- Pandoc Installation
 UI_TEXT_CONTENT["AISTUDIO::TOOLS::SERVICES::PANDOCAVAILABILITYSERVICE::T185447014"] = "Pandoc Installation"