Kitta AI
Use Fish Audio models on Kitta AI
Kitta AI is independently operated by wuwei. Fish Audio provides the models; Kitta AI accounts, credits and API keys belong to this platform. This is not the official Fish Audio website.
Text to speech
Choose a model and voice, preview a short script, then export your audio.
Voice cloning
Create a reusable voice from a recording you own or have permission to use.
Plans and credits
Check membership features and current credit allowances.
API Playground
Test requests and copy examples using a platform API key.
Choose a model and generate speech
Select S2.1 Pro or S2.1 Pro Flash in the text-to-speech workspace. Compare the model descriptions and credit multipliers, choose a voice, and enter a short sample. Listen for pronunciation and delivery before generating and exporting the full script. Model availability and language support are shown in the selector.
Clone an authorized voice
Voice cloning is a member feature. Upload 10 to 60 seconds of clear speech from one speaker, using your own voice or a recording you have permission to use. Each preview uses 20 credits; saving a Fish Audio clone costs no additional credits. Select the saved voice in text to speech to make your voiceover.
Understand trials and usage costs
Free accounts receive signup credits to try text to speech and public voices. Generation costs depend on the selected model and text length; review the estimate before submitting. Membership benefits and credit allowances are listed on the pricing page. A free speech trial does not include access to member-only voice cloning.
Integrate through the platform API
Create an API key in your Kitta AI account, then use the API Playground to test a short request and copy the request example into your application. Review model identifiers, language support and usage costs before integrating. Keys and credits are managed by this platform and are separate from a model provider’s own service.