RunVerseHub
Home / All studios / Voice-Over Studio
Text to voice-over, with dialects and voice cloning

Voice-Over Studio

Paste a script, pick a voice, dialect, age, emotion and speaking rate, and generate the voice-over. You can also clone a voice from a reference clip so the same voice stays consistent across several pieces.

Open Voice-Over Studio →
Sign-in required; new accounts start with 40 permanent credits and 10 free standard images per day.

What it does

Parameters and limits

Model
Qwen3-TTS (voice design / voice cloning), CosyVoice3 (long-form segmentation)
Text per run
≤ 2,000 characters (split into sentences server-side, long scripts are stitched automatically)
Output format
WAV / MP3
Dialects
Standard English plus a range of regional dialects
Reference audio
Used for voice cloning; preview before generating

Pricing

Billing1 credit per 100 characters, ≈$0.01
CapNo cap

Best for

  • Short-video narration and course voice-over
  • Ad narration and product walkthroughs
  • Series content that needs one fixed voice

Not the right fit

  • Long multi-character performances (use Audiobook Studio)
  • Word-level subtitle timing (not offered)

Interface and real output

Script box, dialect, age, emotion and voice description in Voice-Over Studio
Script box, dialect, age, emotion and voice description in Voice-Over Studio

Voice-Over Studio currently has one usable UI capture; the second (mobile and results views) was not taken, and the public gallery has no audio pieces to fill in.

Frequently asked questions

How much text can I convert at once?
Up to 2,000 characters per run. Longer scripts are split into sentences and stitched, but a single submission still stops at 2,000 characters.
How is it billed?
1 credit per 100 characters, with no cap.
Can I clone my own voice?
Yes. Upload a reference clip, preview the result, then use the voice for the real generation.
Are dialects supported?
Yes. Dialect, age, gender, emotion and speaking rate are all selectable parameters.

Other studios