DeutschLernen/GermanApp/Presentation/Controllers/TtsController.cs

using GermanApp.Domain.Interfaces;
using Microsoft.AspNetCore.Authorization;
using Microsoft.AspNetCore.Mvc;

namespace GermanApp.Presentation.Controllers;

/// <summary>
/// API controller for text-to-speech using Coqui TTS.
/// This is part of the Presentation layer.
/// </summary>
[ApiController]
[Route("api/[controller]")]
[Authorize]
public class TtsController : ControllerBase
{
    private readonly ITtsService _ttsService;

    public TtsController(ITtsService ttsService)
    {
        _ttsService = ttsService;
    }

    /// <summary>
    /// Generates audio from text.
    /// </summary>
    /// <param name="request">TTS generation request</param>
    /// <param name="cancellationToken">Cancellation token</param>
    /// <returns>Audio file as bytes</returns>
    [HttpPost("generate")]
    [RequestSizeLimit(5_000_000)] // 5MB limit for response
    public async Task<IActionResult> GenerateAudio(
        [FromBody] TtsGenerationRequest request,
        CancellationToken cancellationToken = default)
    {
        if (string.IsNullOrWhiteSpace(request.Text))
            return BadRequest("Text is required");

        try
        {
            var audioBytes = await _ttsService.GenerateAudioAsync(
                request.Text,
                request.Speaker,
                request.Language,
                cancellationToken);

            // Return audio as WAV or specified format
            var contentType = GetContentType(request.Format);
            return File(audioBytes, contentType);
        }
        catch (TimeoutException ex)
        {
            return StatusCode(504, new { Error = ex.Message });
        }
        catch (Exception ex)
        {
            return StatusCode(500, new { Error = ex.Message });
        }
    }

    /// <summary>
    /// Generates audio and returns a file URL.
    /// </summary>
    /// <param name="request">TTS generation request with filename</param>
    /// <param name="cancellationToken">Cancellation token</param>
    /// <returns>Audio file URL</returns>
    [HttpPost("generate-file")]
    public async Task<IActionResult> GenerateAudioToFile(
        [FromBody] TtsFileGenerationRequest request,
        CancellationToken cancellationToken = default)
    {
        if (string.IsNullOrWhiteSpace(request.Text))
            return BadRequest("Text is required");
        if (string.IsNullOrWhiteSpace(request.Filename))
            return BadRequest("Filename is required");

        try
        {
            var outputPath = Path.Combine("audio", "tts", request.Filename);
            await _ttsService.GenerateAudioToFileAsync(
                request.Text,
                outputPath,
                request.Speaker,
                request.Language,
                cancellationToken);

            return Ok(new TtsFileResponse(
                Url: $"/audio/tts/{request.Filename}",
                Filename: request.Filename));
        }
        catch (Exception ex)
        {
            return StatusCode(500, new { Error = ex.Message });
        }
    }

    /// <summary>
    /// Tests the TTS service.
    /// </summary>
    /// <returns>Health check result</returns>
    [HttpGet("health")]
    [AllowAnonymous]
    public async Task<IActionResult> HealthCheck(CancellationToken cancellationToken = default)
    {
        try
        {
            var isHealthy = await _ttsService.TestModelAsync(cancellationToken);
            return Ok(new { Healthy = isHealthy });
        }
        catch (Exception ex)
        {
            return StatusCode(500, new { Error = ex.Message });
        }
    }

    /// <summary>
    /// Gets information about the current TTS model.
    /// </summary>
    /// <returns>Model information</returns>
    [HttpGet("model-info")]
    [AllowAnonymous]
    public async Task<IActionResult> GetModelInfo(CancellationToken cancellationToken = default)
    {
        try
        {
            var (modelName, modelPath) = await _ttsService.GetModelInfoAsync();
            return Ok(new { ModelName = modelName, ModelPath = modelPath });
        }
        catch (Exception ex)
        {
            return StatusCode(500, new { Error = ex.Message });
        }
    }

    /// <summary>
    /// Gets list of available voices/speakers.
    /// </summary>
    /// <returns>List of speaker IDs</returns>
    [HttpGet("speakers")]
    [AllowAnonymous]
    public async Task<IActionResult> GetSpeakers(CancellationToken cancellationToken = default)
    {
        try
        {
            var speakers = await _ttsService.GetAvailableSpeakersAsync(cancellationToken);
            return Ok(new { Speakers = speakers });
        }
        catch (Exception ex)
        {
            return StatusCode(500, new { Error = ex.Message });
        }
    }

    /// <summary>
    /// Gets the content type for the specified audio format.
    /// </summary>
    private string GetContentType(string? format)
    {
        format = format?.ToLower() ?? "wav";
        return format switch
        {
            "wav" => "audio/wav",
            "mp3" => "audio/mpeg",
            "ogg" => "audio/ogg",
            "flac" => "audio/flac",
            _ => "audio/wav"
        };
    }
}

/// <summary>
/// Request DTO for TTS generation.
/// </summary>
public record TtsGenerationRequest(
    string Text,
    string? Speaker = null,
    string Language = "de",
    string? Format = null);

/// <summary>
/// Request DTO for TTS file generation.
/// </summary>
public record TtsFileGenerationRequest(
    string Text,
    string Filename,
    string? Speaker = null,
    string Language = "de");

/// <summary>
/// Response DTO for TTS file generation.
/// </summary>
public record TtsFileResponse(
    string Url,
    string Filename);