feat: conversor de audio

Areas/AudioTools/Controllers/SpeechToTextController.cs

@@ -0,0 +1,69 @@
+using Microsoft.AspNetCore.Mvc;
+using Convert_It_Online.Services;
+using Microsoft.AspNetCore.Localization;
+
+namespace Convert_It_Online.Areas.AudioTools.Controllers
+{
+    [Area("AudioTools")]
+    [Route("{culture}/[area]/[controller]")]
+    [Route("[area]/[controller]")] // Adicionado para Share Target sem cultura fixa
+    public class SpeechToTextController : Controller
+    {
+        private readonly IAudioTranscriptionService _transcriptionService;
+        private readonly ILogger<SpeechToTextController> _logger;
+
+        public SpeechToTextController(IAudioTranscriptionService transcriptionService, ILogger<SpeechToTextController> logger)
+        {
+            _transcriptionService = transcriptionService;
+            _logger = logger;
+        }
+
+        [HttpGet]
+        public IActionResult Index()
+        {
+            return View();
+        }
+
+        [HttpPost]
+        public async Task<IActionResult> Transcribe(IFormFile audioFile)
+        {
+            if (audioFile == null || audioFile.Length == 0)
+            {
+                ViewBag.Error = "Por favor, selecione um arquivo de áudio.";
+                return View("Index");
+            }
+
+            var culture = HttpContext.Features.Get<IRequestCultureFeature>()?.RequestCulture.UICulture.Name ?? "pt-BR";
+            var tempPath = Path.GetTempFileName();
+
+            try
+            {
+                using (var stream = new FileStream(tempPath, FileMode.Create))
+                {
+                    await audioFile.CopyToAsync(stream);
+                }
+
+                var transcription = await _transcriptionService.TranscribeAsync(tempPath, culture);
+                ViewBag.Result = transcription;
+            }
+            catch (Exception ex)
+            {
+                _logger.LogError(ex, "Erro no controller ao transcrever.");
+                ViewBag.Error = "Erro ao processar o áudio. Verifique se o formato é suportado.";
+            }
+            finally
+            {
+                if (System.IO.File.Exists(tempPath)) System.IO.File.Delete(tempPath);
+            }
+
+            return View("Index");
+        }
+
+        [HttpPost("HandleShare")]
+        public async Task<IActionResult> HandleShare(IFormFile audio)
+        {
+            // O Android via Share Target costuma enviar como 'audio' ou 'file'
+            return await Transcribe(audio);
+        }
+    }
+}

Areas/AudioTools/Controllers/TextToSpeechController.cs

@@ -0,0 +1,15 @@
+using Microsoft.AspNetCore.Mvc;
+
+namespace Convert_It_Online.Areas.AudioTools.Controllers
+{
+    [Area("AudioTools")]
+    [Route("{culture}/[area]/[controller]")]
+    public class TextToSpeechController : Controller
+    {
+        [HttpGet]
+        public IActionResult Index()
+        {
+            return View();
+        }
+    }
+}

Areas/AudioTools/Views/SpeechToText/Index.cshtml

@@ -0,0 +1,69 @@
+@{
+    ViewData["Title"] = "Áudio para Texto (Transcrição)";
+    var culture = ViewContext.RouteData.Values["culture"] as string ?? "pt-BR";
+}
+
+<div class="text-center mb-5">
+    <h1 class="display-4">@ViewData["Title"]</h1>
+    <p class="lead">Converta áudios do WhatsApp, reuniões ou gravações em texto automaticamente usando IA.</p>
+</div>
+
+<div class="row justify-content-center">
+    <div class="col-md-8">
+        <div class="card shadow-custom p-4">
+            <form asp-action="Transcribe" method="post" enctype="multipart/form-data">
+                <div class="mb-4">
+                    <label for="audioFile" class="form-label h5">Selecione o arquivo de áudio</label>
+                    <input type="file" class="form-control form-control-lg" id="audioFile" name="audioFile" accept="audio/*" required>
+                    <div class="form-text mt-2">Formatos suportados: MP3, WAV, OGG, OPUS, M4A, etc.</div>
+                </div>
+
+                <div class="d-grid gap-2">
+                    <button type="submit" class="btn btn-primary btn-lg">
+                        <i class="bi bi-mic-fill me-2"></i>Transcrever Áudio
+                    </button>
+                </div>
+            </form>
+
+            @if (ViewBag.Error != null)
+            {
+                <div class="alert alert-danger mt-4" role="alert">
+                    <i class="bi bi-exclamation-triangle-fill me-2"></i>@ViewBag.Error
+                </div>
+            }
+
+            @if (ViewBag.Result != null)
+            {
+                <div class="mt-5">
+                    <h4 class="mb-3">Transcrição:</h4>
+                    <div class="p-3 bg-light border rounded" style="min-height: 150px; white-space: pre-wrap;">@ViewBag.Result</div>
+                    
+                    <div class="mt-3 d-flex gap-2">
+                        <button class="btn btn-outline-secondary btn-sm" onclick="copyTranscription()">
+                            <i class="bi bi-clipboard me-1"></i>Copiar Texto
+                        </button>
+                    </div>
+                </div>
+            }
+        </div>
+
+        <div class="mt-5">
+            <h3 class="h5 mb-3"><i class="bi bi-shield-check me-2"></i>Privacidade e Tecnologia</h3>
+            <p class="text-muted small">
+                Seu áudio é processado usando a tecnologia <strong>OpenAI Whisper</strong> rodando diretamente em nosso servidor. 
+                Não enviamos seus dados para APIs externas e os arquivos temporários são deletados imediatamente após a conversão.
+            </p>
+        </div>
+    </div>
+</div>
+
+@section Scripts {
+    <script>
+        function copyTranscription() {
+            const text = document.querySelector('.bg-light.border.rounded').innerText;
+            navigator.clipboard.writeText(text).then(() => {
+                alert('Transcrição copiada!');
+            });
+        }
+    </script>
+}

Areas/AudioTools/Views/TextToSpeech/Index.cshtml

@@ -0,0 +1,122 @@
+@{
+    ViewData["Title"] = "Texto para Áudio (Voz)";
+}
+
+<div class="text-center mb-5">
+    <h1 class="display-4">@ViewData["Title"]</h1>
+    <p class="lead">Converta qualquer texto em fala usando vozes neurais de alta qualidade.</p>
+</div>
+
+<div class="row justify-content-center">
+    <div class="col-md-8">
+        <div class="card shadow-custom p-4">
+            <div class="mb-4">
+                <label for="textInput" class="form-label h5">Digite ou cole seu texto</label>
+                <textarea class="form-control" id="textInput" rows="6" placeholder="Escreva aqui o que você deseja que seja lido..."></textarea>
+            </div>
+
+            <div class="row mb-4">
+                <div class="col-md-6">
+                    <label for="voiceSelect" class="form-label">Escolher Voz</label>
+                    <select id="voiceSelect" class="form-select"></select>
+                </div>
+                <div class="col-md-3">
+                    <label for="rate" class="form-label">Velocidade</label>
+                    <input type="range" class="form-range" min="0.5" max="2" step="0.1" id="rate" value="1">
+                </div>
+                <div class="col-md-3">
+                    <label for="pitch" class="form-label">Tom</label>
+                    <input type="range" class="form-range" min="0" max="2" step="0.1" id="pitch" value="1">
+                </div>
+            </div>
+
+            <div class="d-grid gap-2 d-md-flex justify-content-md-center">
+                <button type="button" class="btn btn-primary btn-lg px-5" onclick="speak()">
+                    <i class="bi bi-play-fill me-2"></i>Ouvir
+                </button>
+                <button type="button" class="btn btn-outline-danger btn-lg" onclick="stop()">
+                    <i class="bi bi-stop-fill me-2"></i>Parar
+                </button>
+            </div>
+        </div>
+
+        <div class="mt-4 alert alert-info">
+            <i class="bi bi-info-circle me-2"></i> 
+            Esta ferramenta usa as vozes instaladas no seu dispositivo. No Android e Windows, você encontrará opções de vozes neurais muito naturais.
+        </div>
+    </div>
+</div>
+
+@section Scripts {
+    <script>
+        const synth = window.speechSynthesis;
+        const voiceSelect = document.querySelector('#voiceSelect');
+        const textInput = document.querySelector('#textInput');
+        const rate = document.querySelector('#rate');
+        const pitch = document.querySelector('#pitch');
+
+        let voices = [];
+
+        function populateVoiceList() {
+            voices = synth.getVoices().sort(function (a, b) {
+                const aname = a.name.toUpperCase();
+                const bname = b.name.toUpperCase();
+                if (aname < bname) return -1;
+                else if (aname > bname) return 1;
+                else return 0;
+            });
+
+            const selectedIndex = voiceSelect.selectedIndex < 0 ? 0 : voiceSelect.selectedIndex;
+            voiceSelect.innerHTML = '';
+
+            for (let i = 0; i < voices.length; i++) {
+                const option = document.createElement('option');
+                option.textContent = voices[i].name + ' (' + voices[i].lang + ')';
+
+                if (voices[i].default) {
+                    option.textContent += ' -- PADRÃO';
+                }
+
+                option.setAttribute('data-lang', voices[i].lang);
+                option.setAttribute('data-name', voices[i].name);
+                voiceSelect.appendChild(option);
+            }
+            voiceSelect.selectedIndex = selectedIndex;
+        }
+
+        populateVoiceList();
+        if (speechSynthesis.onvoiceschanged !== undefined) {
+            speechSynthesis.onvoiceschanged = populateVoiceList;
+        }
+
+        function speak() {
+            if (synth.speaking) {
+                console.error('speechSynthesis.speaking');
+                return;
+            }
+            if (textInput.value !== '') {
+                const utterThis = new SpeechSynthesisUtterance(textInput.value);
+                utterThis.onend = function (event) {
+                    console.log('SpeechSynthesisUtterance.onend');
+                }
+                utterThis.onerror = function (event) {
+                    console.error('SpeechSynthesisUtterance.onerror');
+                }
+                const selectedOption = voiceSelect.selectedOptions[0].getAttribute('data-name');
+                for (let i = 0; i < voices.length; i++) {
+                    if (voices[i].name === selectedOption) {
+                        utterThis.voice = voices[i];
+                        break;
+                    }
+                }
+                utterThis.pitch = pitch.value;
+                utterThis.rate = rate.value;
+                synth.speak(utterThis);
+            }
+        }
+
+        function stop() {
+            synth.cancel();
+        }
+    </script>
+}

Areas/AudioTools/Views/_ViewImports.cshtml

@@ -0,0 +1,5 @@
+@using Convert_It_Online
+@using Microsoft.AspNetCore.Mvc.Localization
+
+@addTagHelper *, Microsoft.AspNetCore.Mvc.TagHelpers
+@inject IViewLocalizer Localizer

Areas/AudioTools/Views/_ViewStart.cshtml

@@ -0,0 +1,3 @@
+@{
+    Layout = "_Layout";
+}

Convert-It.csproj

@@ -23,6 +23,9 @@
     <PackageReference Include="Serilog.Enrichers.Environment" Version="3.0.1" />
     <PackageReference Include="Serilog.Enrichers.Process" Version="3.0.0" />
     <PackageReference Include="Serilog.Enrichers.Thread" Version="4.0.0" />
+    <PackageReference Include="Whisper.net" Version="1.9.0" />
+    <PackageReference Include="Whisper.net.Runtime" Version="1.9.0" />
+    <PackageReference Include="Xabe.FFmpeg" Version="6.0.2" />
   </ItemGroup>
 
   </Project>

Dockerfile

@@ -44,6 +44,14 @@ FROM base AS final
 WORKDIR /app
 COPY --from=publish /app/publish .
 
+# Instalar ffmpeg e bibliotecas nativas (rodar como root)
+USER root
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    libc6-dev \
+    && rm -rf /var/lib/apt/lists/*
+USER app
+
 # Variáveis de ambiente otimizadas para produção
 ENV DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=false
 ENV DOTNET_USE_POLLING_FILE_WATCHER=true

Program.cs

@@ -163,6 +163,7 @@ builder.Host.UseSerilog();
 builder.Services.AddLocalization();
 
 builder.Services.AddSingleton<IUrlTranslationService, UrlTranslationService>();
+builder.Services.AddSingleton<IAudioTranscriptionService, AudioTranscriptionService>();
 
 var supportedCultures = new[] { "pt-BR", "es-MX", "es-CL", "es-PY" };
 builder.Services.Configure<RequestLocalizationOptions>(options =>

Readme.md

@@ -1 +1,47 @@
-
+# Convert-It Online
+
+Ferramenta multiuso de conversão de arquivos (Imagens, Documentos, Texto e Áudio) desenvolvida em ASP.NET Core 8 MVC.
+
+## 🛠️ Funcionalidades
+- **Imagens:** HEIC para JPG, JPG para WebP.
+- **Documentos:** PDF para Texto, Extração de Linha Digitável de Boletos (Barcode).
+- **Texto:** Conversor de Case (Maiúsculo/Minúsculo).
+- **Áudio:** Transcrição de Áudio para Texto (Whisper AI) e Texto para Voz (Web Speech API).
+- **PWA:** Suporte a instalação e integração com menu de compartilhamento do Android (Share Target).
+
+## 🚀 Dependências Externas (Obrigatório)
+
+Para as funcionalidades de áudio (transcrição), o projeto depende do **FFmpeg**.
+
+### 🐧 Linux (Ubuntu/Debian)
+```bash
+sudo apt update
+sudo apt install ffmpeg
+```
+
+### 🪟 Windows
+1. Baixe os binários em [ffmpeg.org](https://ffmpeg.org/download.html).
+2. Extraia para uma pasta (ex: `C:\ffmpeg`).
+3. Adicione a pasta `bin` (ex: `C:\ffmpeg\bin`) às **Variáveis de Ambiente do Sistema (PATH)**.
+4. Reinicie o terminal ou o Visual Studio.
+
+### 🐳 Docker
+A imagem Docker já está configurada para instalar o `ffmpeg` automaticamente durante o build.
+
+## 💻 Desenvolvimento Local
+
+1. Certifique-se de ter o .NET 8 SDK instalado.
+2. Clone o repositório.
+3. Configure o FFmpeg conforme instruções acima.
+4. Execute o comando:
+   ```bash
+   dotnet run
+   ```
+
+## 📱 PWA & Android Share Target
+O projeto está configurado como um Progressive Web App. Ao "Instalar" o site no Android:
+1. Ele aparecerá como um aplicativo nativo.
+2. Você poderá compartilhar arquivos de áudio diretamente do WhatsApp para o Convert-It para transcrição automática.
+
+---
+Desenvolvido por Ricardo.

Services/AudioTranscriptionService.cs

@@ -0,0 +1,97 @@
+using System;
+using System.IO;
+using System.Net.Http;
+using System.Threading.Tasks;
+using Whisper.net;
+using Whisper.net.Ggml;
+using Xabe.FFmpeg;
+using Microsoft.Extensions.Logging;
+
+namespace Convert_It_Online.Services
+{
+    public class AudioTranscriptionService : IAudioTranscriptionService
+    {
+        private readonly string _modelPath;
+        private readonly ILogger<AudioTranscriptionService> _logger;
+        private readonly HttpClient _httpClient;
+
+        public AudioTranscriptionService(ILogger<AudioTranscriptionService> logger)
+        {
+            _logger = logger;
+            _httpClient = new HttpClient();
+            _modelPath = Path.Combine(AppContext.BaseDirectory, "Models", "ggml-base.bin");
+            
+            // Garantir que a pasta Models existe
+            var modelsDir = Path.GetDirectoryName(_modelPath);
+            if (!Directory.Exists(modelsDir))
+            {
+                Directory.CreateDirectory(modelsDir!);
+            }
+        }
+
+        private async Task EnsureModelExistsAsync()
+        {
+            if (!System.IO.File.Exists(_modelPath))
+            {
+                _logger.LogInformation("Baixando modelo Whisper Base...");
+                var downloader = new WhisperGgmlDownloader(_httpClient);
+                using var modelStream = await downloader.GetGgmlModelAsync(GgmlType.Base);
+                using var fileStream = System.IO.File.Create(_modelPath);
+                await modelStream.CopyToAsync(fileStream);
+                _logger.LogInformation("Modelo Whisper baixado com sucesso.");
+            }
+        }
+
+        public async Task<string> TranscribeAsync(string inputPath, string culture = "pt-BR")
+        {
+            await EnsureModelExistsAsync();
+
+            string tempWavPath = Path.Combine(Path.GetTempPath(), $"{Guid.NewGuid()}.wav");
+
+            try
+            {
+                _logger.LogInformation("Convertendo áudio para WAV 16kHz Mono...");
+                
+                // Configurar FFmpeg (assume que está no PATH em Linux)
+                // Se estiver no Windows, pode precisar de FFmpeg.SetExecutablesPath
+                
+                var conversion = await FFmpeg.Conversions.New()
+                    .AddParameter($"-i \"{inputPath}\"")
+                    .AddParameter("-ar 16000")
+                    .AddParameter("-ac 1")
+                    .AddParameter("-c:a pcm_s16le")
+                    .SetOutput(tempWavPath)
+                    .Start();
+
+                _logger.LogInformation("Iniciando transcrição com Whisper...");
+
+                using var factory = WhisperFactory.FromPath(_modelPath);
+                using var processor = factory.CreateBuilder()
+                    .WithLanguage(culture.Split('-')[0]) // Usa "pt", "es", etc
+                    .Build();
+
+                using var wavStream = System.IO.File.OpenRead(tempWavPath);
+                
+                var result = "";
+                await foreach (var segment in processor.ProcessAsync(wavStream))
+                {
+                    result += segment.Text + " ";
+                }
+
+                return result.Trim();
+            }
+            catch (Exception ex)
+            {
+                _logger.LogError(ex, "Erro durante a transcrição de áudio.");
+                throw;
+            }
+            finally
+            {
+                if (System.IO.File.Exists(tempWavPath))
+                {
+                    System.IO.File.Delete(tempWavPath);
+                }
+            }
+        }
+    }
+}

Services/IAudioTranscriptionService.cs

@@ -0,0 +1,9 @@
+using System.Threading.Tasks;
+
+namespace Convert_It_Online.Services
+{
+    public interface IAudioTranscriptionService
+    {
+        Task<string> TranscribeAsync(string inputPath, string culture = "pt-BR");
+    }
+}

Views/Shared/_Layout.cshtml

@@ -29,6 +29,7 @@
     <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bootstrap@5.3.2/dist/css/bootstrap.min.css" />
     <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bootstrap-icons@1.11.3/font/bootstrap-icons.min.css">
     <link rel="stylesheet" href="~/css/site.css" />
+    <link rel="manifest" href="~/manifest.json" />
 
     @if (adEnabled && adProvider == "Google" && !string.IsNullOrEmpty(googlePublisherId))
     {
@@ -85,6 +86,19 @@
                                 </a></li>
                             </ul>
                         </li>
+                        <li class="nav-item dropdown mx-2">
+                            <a class="nav-link dropdown-toggle" href="#" id="audioToolsDropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
+                                <i class="bi bi-mic me-1"></i>Áudio
+                            </a>
+                            <ul class="dropdown-menu" aria-labelledby="audioToolsDropdown">
+                                <li><a class="dropdown-item" href="@Html.LocalizedUrl("AudioTools", "SpeechToText")">
+                                    <i class="bi bi-chat-left-text me-2"></i>Áudio para Texto
+                                </a></li>
+                                <li><a class="dropdown-item" href="@Html.LocalizedUrl("AudioTools", "TextToSpeech")">
+                                    <i class="bi bi-megaphone me-2"></i>Texto para Áudio
+                                </a></li>
+                            </ul>
+                        </li>
                     </ul>
                     <div class="dropdown">
                         <button class="btn btn-secondary dropdown-toggle" type="button" id="languageDropdown" data-bs-toggle="dropdown" aria-expanded="false">
@@ -226,6 +240,11 @@
     </footer>
 
     <script src="https://cdn.jsdelivr.net/npm/bootstrap@5.3.2/dist/js/bootstrap.bundle.min.js"></script>
+    <script>
+        if ('serviceWorker' in navigator) {
+            navigator.serviceWorker.register('/sw.js');
+        }
+    </script>
     @await RenderSectionAsync("Scripts", required: false)
 </body>
 </html>

wwwroot/manifest.json

@@ -0,0 +1,29 @@
+{
+  "name": "Convert-It Online",
+  "short_name": "Convert-It",
+  "start_url": "/",
+  "display": "standalone",
+  "background_color": "#0d6efd",
+  "theme_color": "#0d6efd",
+  "description": "Conversores rápidos de imagem, documento e áudio.",
+  "icons": [
+    {
+      "src": "/favicon.ico",
+      "sizes": "64x64",
+      "type": "image/x-icon"
+    }
+  ],
+  "share_target": {
+    "action": "/AudioTools/SpeechToText/HandleShare",
+    "method": "POST",
+    "enctype": "multipart/form-data",
+    "params": {
+      "files": [
+        {
+          "name": "audio",
+          "accept": ["audio/*"]
+        }
+      ]
+    }
+  }
+}

wwwroot/sw.js

@@ -0,0 +1,7 @@
+self.addEventListener('install', (e) => {
+  // Instalado
+});
+
+self.addEventListener('fetch', (e) => {
+  // Necessário para ser instalável
+});