vocodedev
[Feature]: Support for Deepgram Text to Speech Models
Brief Description
I have been using Vocodedev for various voice synthesis tasks and have found it to be an excellent tool. However, I noticed that in the "Synthesizers (Voice)" section of the documentation, there is currently no support for the TTS models offered by Deepgram, specifically the Aura Model.
Rationale
Enhanced Voice Quality: Deepgram's TTS models, such as the Aura Model, provide superior voice quality, which would improve the overall output of Vocodedev.
Lower Latency: The Aura Model offers lower latency, making it ideal for real-time applications and improving user experience.
Consistency: Since Vocodedev already supports Deepgram for Transcribers (Speech-to-Text), including support for their TTS models would create a more cohesive and comprehensive tool.
Suggested Implementation
No response
