feat: Add ModelsLab TTS provider

[adhikjoshi]

Summary

Adds ModelsLab as a new TTS provider for podcastfy, following the same factory/registry pattern as the existing ElevenLabs, OpenAI, Gemini, and Edge integrations.

Changes

File	Change
podcastfy/tts/providers/modelslab.py	New ModelsLabTTS class implementing TTSProvider
podcastfy/tts/factory.py	Register 'modelslab': ModelsLabTTS in _providers
podcastfy/conversation_config.yaml	Add modelslab: config section with default voices
tests/test_audio.py	Add skipped integration test

Usage

from podcastfy.text_to_speech import TextToSpeech

tts = TextToSpeech(model='modelslab', api_key='YOUR_MODELSLAB_API_KEY')
tts.convert_to_speech(podcast_text, 'output.mp3')

Or set the MODELSLAB_API_KEY environment variable and just pass model='modelslab'.

Features

• 10 voices: Bella, Antoni, Elli, Josh, Arnold, Adam, Sam, Rachel, Domi, Gigi
• Default podcast voices: Bella (Person1/question) + Antoni (Person2/answer)
• Async polling: handles status: "processing" responses (polls every 5s, up to 5 min)
• 2,500-char limit: enforced automatically per ModelsLab API constraints
• No new dependencies: uses only requests (already in project dependencies)

conversation_config.yaml

modelslab:
  default_voices:
    question: "Bella"
    answer: "Antoni"
  model: "modelslab-tts-v1"

About ModelsLab

ModelsLab is an AI inference platform offering TTS, image generation, and video generation via REST API. API docs: https://docs.modelslab.com/text-to-audio/realtime/tts