Voice cloning
Clones a voice from about 10 seconds of audio with instant clones, and offers professional voice cloning on higher plans.
Find alternatives to Voice cloning
What it does
- Text to speech
Sources
- Pricing
-
Voice cloning page: "Instant clones carry no training cost. Clone limits per account scale with plan tier." and "Training a pro clone costs 1M credits as a one-off." The pricing page's Free plan card lists text-to-speech, speech-to-text and voice design only and plan M adds pro voice cloning; no sentence says whether the Free plan can create instant clones, so no free or paid model is written.
- Description
-
Official documentation · 16 Nov 2026
Page quote: "Clone any voice from 10s of audio"
- What it does
-
Official documentation · 16 Nov 2026
Page quote: "Clone any voice from 10s of audio"
- Sold within
-
Voice cloning page: "Instant clones carry no training cost. Clone limits per account scale with plan tier." and "Training a pro clone costs 1M credits as a one-off." The pricing page's Free plan card lists text-to-speech, speech-to-text and voice design only and plan M adds pro voice cloning; no sentence says whether the Free plan can create instant clones, so no free or paid model is written.
- Name
-
Official documentation · 16 Nov 2026
Models menu label "Voice cloning" on the pricing page and the product page heading.
- URL
-
Official documentation · 16 Nov 2026
Page quote: "Clone any voice from 10s of audio"
- Deployment
-
Official documentation · 16 Nov 2026
Page quote: "Clone any voice from 10s of audio" The pages read describe a vendor-run web service and no other deployment model, so saas is the vendor-operated reading.
- Interfaces
-
Official documentation · 16 Nov 2026
Product page: "Get an API key Read the API reference"
Also from Gradium
-
Text-to-Speech Model API
Gradium's Text-to-Speech converts text into streaming speech for voice applications.
-
Speech-to-text Model API
Streaming speech-to-text API with semantic turn detection, keyword boosting and tunable latency over one WebSocket.
-
Voice Design Model API
Creates a new synthetic voice from a short text description of the speaker.
-
Live translation Model API
Voice-to-voice translation in real time that renders a speaker's words in another language while they are still speaking.
Something wrong here? Send a correction — quote this product id: gradium-voice-cloning.