Text to speech generation
Text To Speech (TTS) models have made great strides in quality over the last few years. Unfortunately, it's not currently possible to use these libraries without installing a large number of dependencies. The txtai TextToSpeech pipeline has the follo...
Responses
Markdown supported · ⌘↵ to post
douzatan
Could the examples carry the sample rate returned by the selected model through playback, transcription and export, instead of assigning 22050 separately? That would make model substitutions easier to check. For audio intended for a Leadde explainer, I would also keep a short listening test with names, abbreviations and pauses. The transcription round trip checks whether words can be recovered, while listening catches delivery problems that the recovered text alone cannot describe.