search

PromtEngineer / Verbi

A modular voice assistant application for experimenting with state-of-the-art transcription, response generation, and text-to-speech models. Supports OpenAI, Groq, Elevanlabs, CartesiaAI, and Deepgram APIs, plus local models via Ollama. Ideal for research and development in voice technology.
MIT License
123 stars 35 forks source link

MelloTTS /generate-audio/ 404 Not Found #11

Closed replete closed 3 weeks ago

replete commented 3 weeks ago

MeloTTS running locally from docker, WebUI generates audio files, but the /generate-audio endpoint called by Verbi to MeloTTS results in a 404.

I've looked through the MeloTTS project and can't see any references to /generate-audio

$ python3 run_voice_assistant.py
pygame 2.5.2 (SDL 2.28.3, Python 3.12.3)
Hello from the pygame community. https://www.pygame.org/contribute.html
2024-06-06 15:00:08,387 - INFO - Calibrating for ambient noise...
2024-06-06 15:00:09,369 - INFO - Recording started
2024-06-06 15:00:12,251 - INFO - Recording complete
2024-06-06 15:00:12,917 - INFO - No transcription was returned. Starting recording again.
2024-06-06 15:00:13,094 - INFO - Calibrating for ambient noise...
2024-06-06 15:00:14,079 - INFO - Recording started
2024-06-06 15:00:19,776 - INFO - Recording complete
2024-06-06 15:00:21,105 - INFO - You said: Hello Prompt Engineer, this is a recording, but for some reason, there's no response.
2024-06-06 15:00:23,435 - INFO - HTTP Request: POST http://127.0.0.1:11434/api/chat "HTTP/1.1 200 OK"
2024-06-06 15:00:23,435 - INFO - Response: Greetings! I'm here to assist you. Is there anything I can help you with today?
2024-06-06 15:00:23,439 - ERROR - Failed to convert text to speech: 404 Client Error: Not Found for url: http://localhost:8888/generate-audio/
2024-06-06 15:00:23,491 - ERROR - Failed to play audio: No file 'output.mp3' found in working directory '/Users/dev/Verbi'.
2024-06-06 15:00:23,667 - INFO - Calibrating for ambient noise...
2024-06-06 15:00:24,646 - INFO - Recording started