OpenVoice | Lepton AI Playground

Open Voice

Text (162/2000)

Reference speaker

Emotion

Result

For multi-lingual and cross-lingual examples, please refer tothis jupyter notebook.This online demo mainly supports English. The default emotion also supports Chinese. But OpenVoice can adapt to any other language as long as a base speaker is provided.

And use it in the following codes.

import os
from leptonai.client import Client

api_token = os.environ.get('LEPTON_API_TOKEN')
c = Client("https://openvoice.lepton.run", token=api_token)

mpeg=c.run(
    reference_speaker="https://www.lepton.ai/playground/openvoice/inputs/speaker_1.mp3",
    text="Hi, can you hear me?",
    emotion="friendly"
)

# save as mp3 file
with open('output.mp3', 'wb') as f:
    f.write(mpeg)

The rate limit for the Model APIs is 10 requests per minute across all models under Basic Plan. For the pricing plan, you may check out pricing page, If you need a higher rate limit with SLA or dedicated deployment, please contact us.