Added transcription providers (#619)

app/MindWork AI Studio/Provider/AlibabaCloud/ProviderAlibabaCloud.cs

@@ -131,8 +131,17 @@ public sealed class ProviderAlibabaCloud() : BaseProvider(LLMProviders.ALIBABA_C
         
         return this.LoadModels(["text-embedding-"], token, apiKeyProvisional).ContinueWith(t => t.Result.Concat(additionalModels).OrderBy(x => x.Id).AsEnumerable(), token);
     }
-    
-    
+
+    #region Overrides of BaseProvider
+
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
+
+    #endregion
+
     #endregion
     
     private async Task<IEnumerable<Model>> LoadModels(string[] prefixes, CancellationToken token, string? apiKeyProvisional = null)

app/MindWork AI Studio/Provider/Anthropic/ProviderAnthropic.cs

@@ -136,6 +136,12 @@ public sealed class ProviderAnthropic() : BaseProvider(LLMProviders.ANTHROPIC, "
         return Task.FromResult(Enumerable.Empty<Model>());
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
+    
     #endregion
     
     private async Task<IEnumerable<Model>> LoadModels(CancellationToken token, string? apiKeyProvisional = null)

app/MindWork AI Studio/Provider/BaseProvider.cs

@@ -97,6 +97,9 @@ public abstract class BaseProvider : IProvider, ISecretId
     
     /// <inheritdoc />
     public abstract Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default);
+
+    /// <inheritdoc />
+    public abstract Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default);
     
     #endregion
     

app/MindWork AI Studio/Provider/DeepSeek/ProviderDeepSeek.cs

@@ -99,6 +99,11 @@ public sealed class ProviderDeepSeek() : BaseProvider(LLMProviders.DEEP_SEEK, "h
         return Task.FromResult(Enumerable.Empty<Model>());
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
 
     #endregion
 

app/MindWork AI Studio/Provider/Fireworks/ProviderFireworks.cs

@@ -100,5 +100,16 @@ public class ProviderFireworks() : BaseProvider(LLMProviders.FIREWORKS, "https:/
         return Task.FromResult(Enumerable.Empty<Model>());
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult<IEnumerable<Model>>(
+            new List<Model>
+            {
+                new("whisper-v3", "Whisper v3"),
+                new("whisper-v3-turbo", "Whisper v3 Turbo"),
+            });
+    }
+    
     #endregion
 }

app/MindWork AI Studio/Provider/GWDG/ProviderGWDG.cs

@@ -101,6 +101,17 @@ public sealed class ProviderGWDG() : BaseProvider(LLMProviders.GWDG, "https://ch
         return models.Where(model => model.Id.StartsWith("e5-", StringComparison.InvariantCultureIgnoreCase));
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        // Source: https://docs.hpc.gwdg.de/services/saia/index.html#voice-to-text
+        return Task.FromResult<IEnumerable<Model>>(
+            new List<Model>
+            {
+                new("whisper-large-v2", "Whisper v2 Large"),
+            });
+    }
+    
     #endregion
 
     private async Task<IEnumerable<Model>> LoadModels(CancellationToken token, string? apiKeyProvisional = null)

app/MindWork AI Studio/Provider/Google/ProviderGoogle.cs

@@ -112,6 +112,11 @@ public class ProviderGoogle() : BaseProvider(LLMProviders.GOOGLE, "https://gener
             .Select(n => new Provider.Model(n.Name.Replace("models/", string.Empty), n.DisplayName));
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Provider.Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Provider.Model>());
+    }
     
     #endregion
 

app/MindWork AI Studio/Provider/Groq/ProviderGroq.cs

@@ -100,6 +100,12 @@ public class ProviderGroq() : BaseProvider(LLMProviders.GROQ, "https://api.groq.
         return Task.FromResult(Enumerable.Empty<Model>());
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
+    
     #endregion
 
     private async Task<IEnumerable<Model>> LoadModels(CancellationToken token, string? apiKeyProvisional = null)

app/MindWork AI Studio/Provider/Helmholtz/ProviderHelmholtz.cs

@@ -105,6 +105,12 @@ public sealed class ProviderHelmholtz() : BaseProvider(LLMProviders.HELMHOLTZ, "
             model.Id.Contains("gritlm", StringComparison.InvariantCultureIgnoreCase));
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
+    
     #endregion
 
     private async Task<IEnumerable<Model>> LoadModels(CancellationToken token, string? apiKeyProvisional = null)

app/MindWork AI Studio/Provider/HuggingFace/ProviderHuggingFace.cs

@@ -104,5 +104,11 @@ public sealed class ProviderHuggingFace : BaseProvider
         return Task.FromResult(Enumerable.Empty<Model>());
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
+    
     #endregion
 }

app/MindWork AI Studio/Provider/IProvider.cs

@@ -74,4 +74,11 @@ public interface IProvider
     /// <returns>The list of embedding models.</returns>
     public Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default);
     
+    /// <summary>
+    /// Load all possible transcription models that can be used with this provider.
+    /// </summary>
+    /// <param name="apiKeyProvisional">The provisional API key to use. Useful when the user is adding a new provider. When null, the stored API key is used.</param>
+    /// <param name="token">>The cancellation token.</param>
+    /// <returns>>The list of transcription models.</returns>
+    public Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default);
 }

app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs

@@ -110,7 +110,7 @@ public static class LLMProvidersExtensions
     /// </summary>
     /// <param name="llmProvider">The provider to check.</param>
     /// <returns>True if the provider supports embeddings; otherwise, false.</returns>
-    public static bool ProvideEmbeddings(this LLMProviders llmProvider) => llmProvider switch
+    public static bool ProvideEmbeddingAPI(this LLMProviders llmProvider) => llmProvider switch
     {
         //
         // Providers that support embeddings:
@@ -141,6 +141,43 @@ public static class LLMProvidersExtensions
         
         _ => false,
     };
+    
+    public static bool ProvideTranscriptionAPI(this LLMProviders llmProvider) => llmProvider switch
+    {
+        //
+        // Providers that support transcription:
+        //
+        LLMProviders.OPEN_AI => true,
+        LLMProviders.MISTRAL => true,
+        LLMProviders.FIREWORKS => true,
+        LLMProviders.GWDG => true,
+        
+        //
+        // Providers that support transcription but provide no OpenAI-compatible API yet:
+        //
+        LLMProviders.ALIBABA_CLOUD => false,
+        LLMProviders.GOOGLE => false,
+        
+        //
+        // Providers that do not support transcription:
+        //
+        LLMProviders.OPEN_ROUTER => false,
+        LLMProviders.GROQ => false,
+        LLMProviders.ANTHROPIC => false,
+        LLMProviders.X => false,
+        LLMProviders.DEEP_SEEK => false,
+        LLMProviders.HUGGINGFACE => false,
+        LLMProviders.PERPLEXITY => false,
+        
+        LLMProviders.HELMHOLTZ => false,
+
+        //
+        // Self-hosted providers are treated as a special case anyway.
+        //
+        LLMProviders.SELF_HOSTED => true,
+        
+        _ => false,
+    };
 
     /// <summary>
     /// Creates a new provider instance based on the provider value.
@@ -162,6 +199,16 @@ public static class LLMProvidersExtensions
         return embeddingProviderSettings.UsedLLMProvider.CreateProvider(embeddingProviderSettings.Name, embeddingProviderSettings.Host, embeddingProviderSettings.Hostname, embeddingProviderSettings.Model, HFInferenceProvider.NONE);
     }
     
+    /// <summary>
+    /// Creates a new provider instance based on the speech provider value.
+    /// </summary>
+    /// <param name="transcriptionProviderSettings">The speech provider settings.</param>
+    /// <returns>The provider instance.</returns>
+    public static IProvider CreateProvider(this TranscriptionProvider transcriptionProviderSettings)
+    {
+        return transcriptionProviderSettings.UsedLLMProvider.CreateProvider(transcriptionProviderSettings.Name, transcriptionProviderSettings.Host, transcriptionProviderSettings.Hostname, transcriptionProviderSettings.Model, HFInferenceProvider.NONE);
+    }
+    
     private static IProvider CreateProvider(this LLMProviders provider, string instanceName, Host host, string hostname, Model model, HFInferenceProvider inferenceProvider, string expertProviderApiParameter = "")
     {
         try
@@ -274,6 +321,11 @@ public static class LLMProvidersExtensions
         LLMProviders.SELF_HOSTED => host is not Host.LM_STUDIO,
         _ => false,
     };
+    
+    public static bool IsTranscriptionModelProvidedManually(this LLMProviders provider, Host host) => provider switch
+    {
+        _ => false,
+    };
 
     public static bool IsHostNeeded(this LLMProviders provider) => provider switch
     {
@@ -338,13 +390,14 @@ public static class LLMProvidersExtensions
             switch (host)
             {
                 case Host.NONE:
-                case Host.LLAMACPP:
+                case Host.LLAMA_CPP:
                 default:
                     return false;
 
                 case Host.OLLAMA:
                 case Host.LM_STUDIO:
                 case Host.VLLM:
+                case Host.WHISPER_CPP:
                     return true;
             }
         }

app/MindWork AI Studio/Provider/Mistral/ProviderMistral.cs

@@ -113,6 +113,17 @@ public sealed class ProviderMistral() : BaseProvider(LLMProviders.MISTRAL, "http
         return Task.FromResult(Enumerable.Empty<Provider.Model>());
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Provider.Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        // Source: https://docs.mistral.ai/capabilities/audio_transcription
+        return Task.FromResult<IEnumerable<Provider.Model>>(
+            new List<Provider.Model>
+            {
+                new("voxtral-mini-latest", "Voxtral Mini Latest"),
+            });
+    }
+    
     #endregion
     
     private async Task<ModelsResponse> LoadModelList(string? apiKeyProvisional, CancellationToken token)

app/MindWork AI Studio/Provider/NoProvider.cs

@@ -23,6 +23,8 @@ public class NoProvider : IProvider
     public Task<IEnumerable<Model>> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult<IEnumerable<Model>>([]);
     
     public Task<IEnumerable<Model>> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult<IEnumerable<Model>>([]);
+    
+    public Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default) => Task.FromResult<IEnumerable<Model>>([]);
 
     public async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatChatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
     {

app/MindWork AI Studio/Provider/OpenAI/ProviderOpenAI.cs

@@ -241,6 +241,14 @@ public sealed class ProviderOpenAI() : BaseProvider(LLMProviders.OPEN_AI, "https
         return this.LoadModels(["text-embedding-"], token, apiKeyProvisional);
     }
     
+    /// <inheritdoc />
+    public override async Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        var models = await this.LoadModels(["whisper-", "gpt-"], token, apiKeyProvisional);
+        return models.Where(model => model.Id.StartsWith("whisper-", StringComparison.InvariantCultureIgnoreCase) ||
+                                     model.Id.Contains("-transcribe", StringComparison.InvariantCultureIgnoreCase));
+    }
+    
     #endregion
 
     private async Task<IEnumerable<Model>> LoadModels(string[] prefixes, CancellationToken token, string? apiKeyProvisional = null)

app/MindWork AI Studio/Provider/OpenRouter/ProviderOpenRouter.cs

@@ -106,6 +106,12 @@ public sealed class ProviderOpenRouter() : BaseProvider(LLMProviders.OPEN_ROUTER
     {
         return this.LoadEmbeddingModels(token, apiKeyProvisional);
     }
+    
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
 
     #endregion
 

app/MindWork AI Studio/Provider/Perplexity/ProviderPerplexity.cs

@@ -107,6 +107,12 @@ public sealed class ProviderPerplexity() : BaseProvider(LLMProviders.PERPLEXITY,
         return Task.FromResult(Enumerable.Empty<Model>());
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
+    
     #endregion
 
     private Task<IEnumerable<Model>> LoadModels() => Task.FromResult<IEnumerable<Model>>(KNOWN_MODELS);

app/MindWork AI Studio/Provider/SelfHosted/Host.cs

@@ -5,7 +5,8 @@ public enum Host
     NONE,
 
     LM_STUDIO,
-    LLAMACPP,
+    LLAMA_CPP,
+    WHISPER_CPP,
     OLLAMA,
     VLLM,
 }

app/MindWork AI Studio/Provider/SelfHosted/HostExtensions.cs

@@ -7,7 +7,8 @@ public static class HostExtensions
         Host.NONE => "None",
 
         Host.LM_STUDIO => "LM Studio",
-        Host.LLAMACPP => "llama.cpp",
+        Host.LLAMA_CPP => "llama.cpp",
+        Host.WHISPER_CPP => "whisper.cpp",
         Host.OLLAMA => "ollama",
         Host.VLLM => "vLLM",
 
@@ -24,7 +25,28 @@ public static class HostExtensions
         _ => "chat/completions",
     };
     
-    public static bool AreEmbeddingsSupported(this Host host)
+    public static string TranscriptionURL(this Host host) => host switch
+    {
+        _ => "audio/transcriptions",
+    };
+    
+    public static bool IsChatSupported(this Host host)
+    {
+        switch (host)
+        {
+            case Host.WHISPER_CPP:
+                return false;
+            
+            default:
+            case Host.OLLAMA:
+            case Host.VLLM:
+            case Host.LM_STUDIO:
+            case Host.LLAMA_CPP:
+                return true;
+        }
+    }
+    
+    public static bool IsEmbeddingSupported(this Host host)
     {
         switch (host)
         {
@@ -34,7 +56,23 @@ public static class HostExtensions
                 return true;
             
             default:
-            case Host.LLAMACPP:
+            case Host.LLAMA_CPP:
+                return false;
+        }
+    }
+    
+    public static bool IsTranscriptionSupported(this Host host)
+    {
+        switch (host)
+        {
+            case Host.OLLAMA:
+            case Host.VLLM:
+            case Host.WHISPER_CPP:
+                return true;
+            
+            default:
+            case Host.LM_STUDIO:
+            case Host.LLAMA_CPP:
                 return false;
         }
     }

app/MindWork AI Studio/Provider/SelfHosted/ProviderSelfHosted.cs

@@ -6,12 +6,15 @@ using System.Text.Json;
 using AIStudio.Chat;
 using AIStudio.Provider.OpenAI;
 using AIStudio.Settings;
+using AIStudio.Tools.PluginSystem;
 
 namespace AIStudio.Provider.SelfHosted;
 
 public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvider(LLMProviders.SELF_HOSTED, $"{hostname}{host.BaseURL()}", LOGGER)
 {
     private static readonly ILogger<ProviderSelfHosted> LOGGER = Program.LOGGER_FACTORY.CreateLogger<ProviderSelfHosted>();
+    
+    private static string TB(string fallbackEN) => I18N.I.T(fallbackEN, typeof(ProviderSelfHosted).Namespace, nameof(ProviderSelfHosted));
 
     #region Implementation of IProvider
 
@@ -91,7 +94,7 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
         {
             switch (host)
             {
-                case Host.LLAMACPP:
+                case Host.LLAMA_CPP:
                     // Right now, llama.cpp only supports one model.
                     // There is no API to list the model(s).
                     return [ new Provider.Model("as configured by llama.cpp", null) ];
@@ -138,6 +141,35 @@ public sealed class ProviderSelfHosted(Host host, string hostname) : BaseProvide
         }
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Provider.Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        try
+        {
+            switch (host)
+            {
+                case Host.WHISPER_CPP:
+                    return Task.FromResult<IEnumerable<Provider.Model>>(
+                        new List<Provider.Model>
+                        {
+                            new("loaded-model", TB("Model as configured by whisper.cpp")),
+                        });
+                
+                case Host.OLLAMA:
+                case Host.VLLM:
+                    return this.LoadModels([], [], token, apiKeyProvisional);
+                
+                default:
+                    return Task.FromResult(Enumerable.Empty<Provider.Model>());
+            }
+        }
+        catch (Exception e)
+        {
+            LOGGER.LogError(e, "Failed to load transcription models from self-hosted provider.");
+            return Task.FromResult(Enumerable.Empty<Provider.Model>());
+        }
+    }
+    
     #endregion
 
     private async Task<IEnumerable<Provider.Model>> LoadModels(string[] ignorePhrases, string[] filterPhrases, CancellationToken token, string? apiKeyProvisional = null)

app/MindWork AI Studio/Provider/X/ProviderX.cs

@@ -101,6 +101,12 @@ public sealed class ProviderX() : BaseProvider(LLMProviders.X, "https://api.x.ai
         return Task.FromResult<IEnumerable<Model>>([]);
     }
     
+    /// <inheritdoc />
+    public override Task<IEnumerable<Model>> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
+    {
+        return Task.FromResult(Enumerable.Empty<Model>());
+    }
+    
     #endregion
     
     private async Task<IEnumerable<Model>> LoadModels(string[] prefixes, CancellationToken token, string? apiKeyProvisional = null)