Text to Speech

I’d love to see a good-quality local Text-to-Speech tool added to Hangar. The basic use case would simply be: paste or import text, choose a language and natural-sounding voice, and generate an audio file (WAV/MP3) that can be used anywhere. But it would become especially powerful if it could also work with Hangar’s existing subtitle, transcription and video tools. For example, if I have an SRT file, Hangar could use the subtitle text to generate a voiceover while respecting the existing timings, and then optionally use that audio to replace the original audio in a video. It would also be great to support multiple languages and voices, with natural-sounding narration rather than robotic TTS, and make it possible to process several files through Chains or batch workflows.