87d97bba00
Integrates the OpenRouter AI provider using the Vercel AI SDK adapter (@openrouter/ai-sdk-provider). This allows users to configure and utilize models available through the OpenRouter platform. - Added src/ai-providers/openrouter.js with standard Vercel AI SDK wrapper functions (generateText, streamText, generateObject). - Updated ai-services-unified.js to include the OpenRouter provider in the PROVIDER_FUNCTIONS map and API key resolution logic. - Verified config-manager.js handles OpenRouter API key checks correctly. - Users can configure OpenRouter models via .taskmasterconfig using the task-master models command or MCP models tool. Requires OPENROUTER_API_KEY. - Enhanced error handling in ai-services-unified.js to provide clearer messages when generateObjectService fails due to lack of underlying tool support in the selected model/provider endpoint.
37 lines
3.3 KiB
Plaintext
37 lines
3.3 KiB
Plaintext
# Task ID: 74
|
|
# Title: Task 74: Implement Local Kokoro TTS Support
|
|
# Status: pending
|
|
# Dependencies: None
|
|
# Priority: medium
|
|
# Description: Integrate Text-to-Speech (TTS) functionality using a locally running Google Cloud Text-to-Speech (Kokoro) instance, enabling the application to synthesize speech from text.
|
|
# Details:
|
|
Implementation Details:
|
|
1. **Kokoro Setup:** Assume the user has a local Kokoro TTS instance running and accessible via a network address (e.g., http://localhost:port).
|
|
2. **Configuration:** Introduce new configuration options (e.g., in `.taskmasterconfig`) to enable/disable TTS, specify the provider ('kokoro_local'), and configure the Kokoro endpoint URL (`tts.kokoro.url`). Consider adding options for voice selection and language if the Kokoro API supports them.
|
|
3. **API Interaction:** Implement a client module to interact with the local Kokoro TTS API. This module should handle sending text input and receiving audio data (likely in formats like WAV or MP3).
|
|
4. **Audio Playback:** Integrate a cross-platform audio playback library (e.g., `playsound`, `simpleaudio`, or platform-specific APIs) to play the synthesized audio received from Kokoro.
|
|
5. **Integration Point:** Identify initial areas in the application where TTS will be used (e.g., a command to read out the current task's title and description). Design the integration to be extensible for future use cases.
|
|
6. **Error Handling:** Implement robust error handling for scenarios like: Kokoro instance unreachable, API errors during synthesis, invalid configuration, audio playback failures. Provide informative feedback to the user.
|
|
7. **Dependencies:** Add any necessary HTTP client or audio playback libraries as project dependencies.
|
|
|
|
# Test Strategy:
|
|
1. **Unit Tests:**
|
|
* Mock the Kokoro API client. Verify that the TTS module correctly formats requests based on input text and configuration.
|
|
* Test handling of successful API responses (parsing audio data placeholder).
|
|
* Test handling of various API error responses (e.g., 404, 500).
|
|
* Mock the audio playback library. Verify that the received audio data is passed correctly to the playback function.
|
|
* Test configuration loading and validation logic.
|
|
2. **Integration Tests:**
|
|
* Requires a running local Kokoro TTS instance (or a compatible mock server).
|
|
* Send actual text snippets through the TTS module to the local Kokoro instance.
|
|
* Verify that valid audio data is received (e.g., check format, non-zero size). Direct audio playback verification might be difficult in automated tests, focus on the data transfer.
|
|
* Test the end-to-end flow by triggering TTS from an application command and ensuring no exceptions occur during synthesis and playback initiation.
|
|
* Test error handling by attempting synthesis with the Kokoro instance stopped or misconfigured.
|
|
3. **Manual Testing:**
|
|
* Configure the application to point to a running local Kokoro instance.
|
|
* Trigger TTS for various text inputs (short, long, special characters).
|
|
* Verify that the audio is played back clearly and accurately reflects the input text.
|
|
* Test enabling/disabling TTS via configuration.
|
|
* Test behavior when the Kokoro endpoint is incorrect or the server is down.
|
|
* Verify performance and responsiveness.
|