Date | 28/04/2025, 16.00 - 17.00 |
---|---|
Participants | • Michael Suthirta |
• Reynard Adrian | |
• Nathanael Mahardika Susilo | |
• Gilmore | |
• Muhammad Rafi Isnaen |
Membangun fungsi mendasar dari aplikasi yang memungkinkan pengguna dapat berbicara dan memberikan perintah lalu aplikasi memberikan respons untuk pengguna dalam bentuk teks.
Requirements / Features | User story | Importance | Effort (Hours) |
---|---|---|---|
Voice Chat Feature | As an elderly who struggles to type using phone keyboard, I want to be able to use voice commands so that I don't need to type too much. | Must Have | 58 |
Text Output | As an elderly who cannot keep up with voice-based instructions, I want to be able to read the guides so that I can reread it if I forget about it. | Must Have | 37 |
Question | Answer | Answered |
---|---|---|
Bagaimana fitur voice chat bisa di-trigger jika belum ada overlay ? | Membuat tombol yang sangat sederhana untuk dibuild sebelum overlay. | Y |
PBI | Tasks | Effort (hours) | Descriptions |
---|---|---|---|
Voice Chat Feature | Researching about speech-to-text, text-to-speech, and LLAMA 3 API | 15 | |
Voice input receiving system | 6 | ||
Speech to text API integration | 9 | ||
Speech to text input receiving and conversion | 8 | ||
Text to speech output integration | 8 | ||
Error handling message display | 3 | ||
Testing and troubleshooting | 9 | ||
Efforts | 58 | ||
Text output | AI API input integration and passing | 9 | |
AI API output receiving and integration | 8 | ||
Create UI to display the text | 5 | ||
Display text output | 3 | ||
Error handling message display | 3 | ||
Testing and troubleshooting | 9 | ||
Efforts | 37 | ||
Total Efforts | 95 | ||
Members | Tasks | |
---|---|---|
Michael Suthirta | Researching about speech-to-text, text-to-speech, and LLAMA 3 API | |
Voice input receiving system | ||
Text to speech API integration | ||
Text to speech input receiving and conversion | ||
Text to speech output integration | ||
Testing and troubleshooting | ||
Create UI to display the text | ||
Reynard Adrian | Researching about speech-to-text, text-to-speech, and LLAMA 3 API | |
Voice input receiving system | ||
Nathanael Mahardika Susilo | Researching about speech-to-text, text-to-speech, and LLAMA 3 API | |
Create UI to display the text | ||
Display text output | ||
Testing and troubleshooting (Text Output) | ||
Testing and troubleshooting (VC feature) | ||
Error handling message display (Text Output) | ||
Error handling message display (VC feature) | ||
Gilmore | Researching about speech-to-text, text-to-speech, and LLAMA 3 API | |
Voice input receiving system | ||
Text to speech input receiving and conversion | ||
Error handling message display | ||
Testing and troubleshooting (VC feature) | ||
AI API input integration and passing | ||
AI API output receiving and integration | ||
Error handling message display | ||
Testing and troubleshooting (Text Output) | ||
Muhammad Rafi Isnaen | Researching about speech-to-text, text-to-speech, and LLAMA 3 API | |
Text to speech API integration | ||
Text to speech output integration | ||
Display text output | ||
Testing and troubleshooting |
Hour-Based Estimation