I used the F5 TTS tool on Hugging Face and generated over 5 minutes of normal speech and trained it on Google colab for 250 epochs.

I have updated this model since the first time I uploaded it, so please ignore the sample deck as the newer downloadable model I have made now sounds better instead of sounding like nothing like it was before.

Additional Details:

Tags: Electronic Arts, Krome Studios, huggingface, ai-model

Related URL: https://huggingface.co/Ryanham1lton/TySW/resolve/main/Ty.zip?download=true

Download Link: https://huggingface.co/Ryanham1lton/TySW/resolve/main/Ty.zip?download=true Hosted on Hugging Face

Convert this model in EasyAIVoice

Voice accords

Main sonic traits

Selected-sample labels, grouped by what they describe.

Age

child

young adult

elderly

Music use

background music

speaking

singing

Style/timbre

smooth

calm

warm

Use case

podcasts

education and e-learning

conversational

Sample deck

Lean and sweet spot

Pick a pitch, compare the Quality Score, then Run. Hold Ctrl or Cmd to select multiple pitches.

top 0.86 · avg 0.79

female

18

male

0

female base · pitch 0 Quality Score 0.85 · heard as female

Autorun

Run

male

-16 0.79 -12 0.79 -8 0.74 -4 0.78 0 0.80 4 0.76 8 0.77 12 0.73 16 0.76

female

-16 0.83 -12 0.86 -8 0.81 -4 0.78 0 0.85 4 0.82 8 0.82 12 0.76 16 0.78

heard female heard male Quality Score = estimated audio quality, higher is better Ctrl/Cmd-click = select multiple pitches

Similar voices

This voice model sounds like

Nearby voices from generated samples. Pick a pitch in the Sample Deck to refresh the matches.

Finding nearby voices for this pitch...