Use consented audio
Upload a short, clear recording you own or have explicit permission to clone.
ACTIVE · VERIFIED AGAINST THE PRODUCT
Clone Voice
Clone a reusable voice from your own recording or properly consented reference audio, then use it in the unified speech workspace.
Verified operating specifications
Real inputs, limits and controls
- Sample length
- 3–30 seconds
- Upload limit
- 10 MB per reference recording
- Audio formats
- MP3, WAV, M4A, AAC, OGG, WebM, FLAC or Opus
- Cleanup
- Optional background-noise removal before cloning
Core capabilities
What this tool does
Reference-audio workflow
Reusable cloned voices
Unified TTS library
Consent-first use
Connected services
Related voice sources, services or models
This is an internal OpenSpeaker workflow. It is intentionally not mislabeled as a product from an external provider.
Product workflow
From input to finished output in three steps
Prepare the sample
Preview the waveform and optionally remove background noise.
Save and use the voice
Name the clone and select it immediately in the unified TTS library.
Use cases
Good fits
- Personal narration voice
- Consented brand voice
- Recurring character voice
- Localized content continuity
Developer API
Integrate this workflow
Generation tasks are asynchronous: receive a task_id, then poll or use a webhook.
POST/v3/text-to-speech/voice-cloneProduct-verified information
This page only describes capabilities visible in the current application with a corresponding processing path at the latest verification.