Hi

Congratulations on releasing the V1 update. I've integrated the v1 update into AllTalk v2 BETA https://github.com/erew123/alltalk_tts/tree/alltalkbeta

If you are ever interested in making any updates to the setup for AllTalk I happily welcome them and the engine for Parler is here https://github.com/erew123/alltalk_tts/tree/alltalkbeta/system/tts_engines/parler

Through AllTalk there is a full AllTalk API suite, OpenAI v1 TTS API compatible endpoint and integration to Text-gen-webui, kobold and Sillytavern, as well as things like HomeAssistant via the OpenAI compatible API.

My 1x question is How similar should the "Using a specific speaker" consistency be? And does the consistency vary by model?

If it matters to my question, here is how I have setup the voices https://github.com/erew123/alltalk_tts/blob/alltalkbeta/system/tts_engines/parler/parler_voices.json with the "Native" ones being the inbuilt voices.

Thanks