No filming:An AI avatar or clone yourself

    Cartesia · Audio model

    Cartesia Voice Clone: specs, pricing and how to use it

    Clone any voice using Cartesia AI. Upload a short audio sample to instantly create a personalized voice for text-to-speech generation.

    0 credits (free)

    One account for the web and iPhone.

    Cartesia Voice Clone is Cartesia's instant voice cloning, and making a clone on Versely is free. Upload one clip of a single speaker with no music or background noise. Cartesia says 10 seconds is enough to start and up to 60 seconds keeps the speaker's accent better; the longer limit applies to Sonic 3.6 and newer, while older Sonic models learn only from the first 10 seconds. Cartesia's Sonic text-to-speech models on Versely then read any script in that voice. Only clone voices you own or have permission to use.

    What Cartesia Voice Clone is best at

    Voice clone
    Voice CloneCustom VoiceAudio UploadMultilingualHigh Quality

    Pricing

    Cartesia Voice Clone costs 0 credits (free) on Versely.

    Prices are Versely credits. Your plan's credit allowance is on the pricing page.

    Inputs

    Voice sample

    Required - one audio clip of the voice you want to clone: a single speaker, 10 to 60 seconds, no music or background noise, up to 16 MB.

    Release

    Cartesia Voice Clone was released on October 1, 2025 (released 1.1 years ago).

    Other audio models

    Use Cartesia Voice Clone inside these tools

    Frequently asked questions

    How much does Cartesia Voice Clone cost on Versely?+

    Cartesia Voice Clone costs 0 credits (free) on Versely.

    What is Cartesia Voice Clone best for?+

    Clone any voice using Cartesia AI. Upload a short audio sample to instantly create a personalized voice for text-to-speech generation. On Versely it is filed as a Cartesia audio model for voice clone.

    How long should the sample be for a Cartesia voice clone?+

    Cartesia says 10 seconds of audio is enough to start, and up to 60 seconds helps the clone keep the speaker's accent. The 60-second limit applies to Sonic 3.6 and newer. Older Sonic models learn only from the first 10 seconds, so a longer clip does not improve them. The file can be up to 16 MB.

    When was Cartesia Voice Clone released?+

    Cartesia Voice Clone was released on October 1, 2025 (released 1.1 years ago).

    How do I record a good sample for a voice clone?+

    Record one speaker in a quiet room, with no music and no echo. The clone copies the clip's mood, accent, pace and energy, so record the way you want the voice to sound, and speak naturally rather than like an announcer. Use a language the speaker actually speaks: Cartesia builds each clone from one language.

    Is Cartesia voice cloning free on Versely?+

    Yes. Creating the clone costs 0 credits. You pay only when a Cartesia Sonic model reads a script in the cloned voice, billed per 1,000 characters at that model's rate. Each account can keep up to 3 Cartesia clones at a time; delete one to make room for a new one.

    Is this Cartesia's instant clone or its Pro Voice Clone?+

    It is the Instant Voice Clone, made from one short clip in seconds. Cartesia's Pro Voice Clone is a separate product: it fine-tunes a model on at least 30 minutes of studio-quality audio from one speaker, and training takes up to 3 hours. Versely runs the instant clone only.

    Try Cartesia Voice Clone inside Versely

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync, in your browser or on your phone.

    One account for the web and iPhone.

    Versely AI Weekly

    New AI models, every Thursday.

    The image, video, audio and LLM models released that week, what each is good for, and what's new on Versely.

    Weekly. Unsubscribe anytime.