Example Use (from within model directory):

tts --text "this is Text for Tee tee ess" --out_path speech.wav --model_path checkpoint_85000.pth --config_path config.json --speakers_file_path vctk_speakers.json --speaker_idx VCTK_p226 --language_idx en

VCTK_p226: 22 year old male, English accent (Surrey)

VCTK_p227: 38 year old male, English accent (Cumbria)

VCTK_p232: 23 year old male, English accent (Southern England)

VCTK_p243: 22 year old male, English accent (London)

VCTK_p254: 21 year old male, English accent (Surrey)

VCTK_p256: 24 year old male, English accent (Birmingham)

VCTK_p258: 22 year old male, English accent (Southern England)

VCTK_p259: 23 year old male, English accent (Nottingham)

VCTK_p270: 21 year old male, English accent (Yorkshire)

VCTK_p273: 23 year old male, English accent (Suffolk)

VCTK_p274: 22 year old male, English accent (Essex)

VCTK_p278: 22 year old male, English accent (Cheshire)

VCTK_p279: 23 year old male, English accent (Leicester)

VCTK_p286: 23 year old male, English accent (Newcastle)

VCTK_p287: 23 year old male, English accent (York)

Built with YourTTS

Dataset: https://datashare.ed.ac.uk/handle/10283/2950

Downloads last month
26
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.