AI voice generator for text to speech, voice cloning, and voice design
Upscale video to 4K on your own GPU for free, or use cloud AI models
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Freemium
Freemium
Pricing
Not given
Local methods: free and unlimited. Cloud AI: 3 free credits on sign-up; credit packs from $5 (150 credits plus 20% bonus on first top-up); AI Restore ≈95 credits, Video Enhance ≈12 credits, Topaz Proteus ≈68 credits, Topaz Starlight ≈68 credits. Video prices are per 10-second 720p clip enlarged 2×.
Key features
300+ public voices across 6 language groups
Editable text-to-speech with preview before rendering
Permission-based voice cloning from authorized recordings
Prompt-driven voice design to create synthetic speakers
Generation history and reusable voice models
Support for English, Chinese, Japanese, Korean, Spanish, and Portuguese
Maximum 1,000 characters per conversion
24/7 browser-based access without studio booking
Downloadable audio in multiple formats
Revision workflow keeping scripts editable during production
Upscale video 2×, 3× or 4× without upload
Runs entirely in browser on local GPU
Supports H.264, VP9, AV1 codecs
Results stored 30 days for cloud runs
Hardware-accelerated H.264 or VP9 encoding
Works offline for local methods
Precision and generative AI model options
What makes it different
Permission-based voice cloning with consent verification built into the workflow
Edit and revise text within the same workflow without new recording sessions
Account-based browser workspace combining discovery, generation, and export
Independent service separate from Fish Audio
Human-in-the-loop review for accuracy and suitability
Free local upscaling with no upload, watermark or limits
Runs entirely in browser using WebGPU—nothing leaves your device
Pay-per-run cloud models with no subscription required
Fish Voice