edge-tts

You can generate high-quality text-to-speech narration for video production without API keys by running the generate_tts.py script. It leverages Edge TTS to convert scripted text into natural-sounding per-scene voiceovers.

Yes, you can generate synchronized word-level SRT subtitles alongside audio for short-form videos like YouTube Shorts. The text-to-speech process produces per-scene outputs and optional captioning files simultaneously.

You can select different TTS voices by language and gender for multilingual workflows using environment-driven configuration. This allows you to specify voices and adjust rate, volume, and pitch for your narration.

Yes, Edge TTS supports per-scene voiceover generation with adjustable pitch, rate, and volume. You configure these voice parameters via environment variables to produce tailored narration audio for each scene.

The best way to automate narration audio and subtitle creation for short-form videos is running a dedicated script with your project directory. This handles both per-scene text-to-speech audio generation and synchronized SRT creation.

Yes, you need python-dotenv installed to configure Edge TTS voices. It enables environment-driven configuration for selecting languages, genders, and adjusting voice parameters like rate and pitch.