CloneVoice User Guide
Learn the main workflows, upload requirements, task states, credits, and safety rules.
Start with voice cloning
Sign in, upload a permitted sample, confirm consent, name the voice, and submit the training task.
Using CloneVoice
Upload a clear sample between 10 and 300 seconds and no larger than 25 MiB. Confirm that it is your voice and that you authorize training.
Supported: MP3, WAV, M4A, MP4 audio, WebM, and OGG.
Create a voiceChoose a voice you are allowed to use, enter text, review the estimated credit cost, and submit the generation task.
Generate speechBrowse published voices, preview available samples, and select a permitted voice for text-to-speech generation.
Browse public voicesReview your recent tasks, play completed audio, and use the task ID when reporting a problem.
View historyCredit usage is shown before supported actions. Review the current plans and manage an active subscription from your account.
View pricingTasks may remain processing before they complete. If one fails, verify the input requirements, retry once, then contact support with the task ID.
Check task statusCommon questions
Voice training and generation run asynchronously. Check Generation History for the latest state before submitting the same task again.
Use a clear recording of one speaker with little background noise, music, echo, or long silence.
Include the account email, task ID, what you expected, and the error shown. Do not attach passwords or private voice samples.
Only clone your own voice with the required authorization. Do not use generated audio for impersonation, fraud, harassment, or other prohibited activity.
CloneVoice does not currently offer a public API key or SDK. The web application uses authenticated internal routes that are not a supported external integration contract.
Send the account email, task ID, and a concise description of the issue. Do not send passwords or private voice samples.
Contact support