Warm narration
A warm, soft adult voice with a neutral timbre and a moderate-to-slow pace. Clear diction, like telling a travel story in a quiet room. Natural, restrained emotion.
For storytelling and everyday moments.
Choose your own mediaAI voice cloning and design tool
Clone a reference recording or design a new voice from a description, then give it a new script on this page.
Prepare a reference for your next voiceover
These scenarios help you prepare a reference recording. Upload your own audio to create a voice, then reuse it for speech.
Clear explanations
A bright, steady adult voice at a moderate pace with clear logical pauses. Patient and natural, suited to explaining steps and concepts.
For lessons, tutorials and educational videos.
Choose your own mediaAn upbeat introduction
A fresh, youthful adult voice, lightly energetic but never rushed. Natural pauses between phrases, introducing a product or new idea in a friendly way.
For product introductions and short-form openings.
Choose your own mediaFrom a small task to a usable result
Clone a reference recording or design a new voice from a description, then give it a new script on this page.
Try the toolUse a recording as the reference
Choose a reference recording. Clear speech from one speaker helps provide consistent voice information. Avoid background music and overlapping speakers.
Separate the voice from the script
The recording creates a voice; it is not simply converted into another format. Once created, the voice can read a new script.
Carry the voice into your next piece
The result includes a voice ID and a link to speech generation. Reuse the matching model in the same workspace with less setup.
How to use voice clone
Prepare your input, choose settings and review the result.
- 1
Choose how to create
Upload a clear recording to clone, or switch to voice design and enter a description and preview text.
- 2
Review and create
Review the model and credit quote for the selected creation method.
- 3
Give it a new script
After creation, choose “Generate speech with this voice” and enter a new script on this page.
A few things before you start
Common questions about usage, pricing, files and results.
More questions? Contact usDo I need an account, and how is it billed?
Sign in to DraPub with an available cloud workspace. Generation uses credits. Review the quote for your model and settings before submitting.
Are prompts and files uploaded?
When you submit, your prompt and input media are sent to the cloud for the task. Results are saved as assets in the selected workspace for preview and download.
What reference audio should I use?
Use clear speech from a single speaker without strong noise, music or overlapping voices. The tool accepts one audio file up to 100 MB; provider format and duration rules also apply.
Can I upload several recordings at once?
Each request accepts one reference file. It does not automatically combine recordings or multiple speakers.
How do I listen to the cloned voice?
Cloning returns a voice ID. Choose “Generate speech with this voice” and submit a short script to listen. Speech generation has its own quote.
Can another account use the voice?
The voice is available only to the account and workspace that created it, with its matching speech model.
Keep your next step close
A few related tools for the work that comes next.
Bring a recording and create your next voice
Choose a model, review the price, then decide to generate.