Wan · Lipsync model

    Wan 2.2 Speech to Video

    Generates high-quality videos from static images and audio with realistic facial expressions, body movements, and professional camera work

    50 creditsUp to 720p2 variants

    What Wan 2.2 Speech to Video is best at

    Audio to lipsyncImage to lipsync
    RealisticHigh qualityTalking headFacial expressionsBody movementsProfessional

    Pricing

    Wan 2.2 Speech to Video costs 50 credits on Versely. It bills per second, at a rate that changes with output resolution, so a full job runs 50 to 2400 credits depending on output resolution.

    OptionPrice
    SD10 credits
    HD/4K20 credits

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

    Wan 2.2 Speech to Video variants

    Versely runs 2 versions of this model — tiers and input modes share the same underlying model, so they live here rather than on 2 near-identical pages. Prices range from 50 to 50 credits.

    VariantModeTierCreditsMax resolutionDurations
    Wan 2.2 Speech Turboimage to lipsyncTurbo501080p
    Wan 2.2 Speech to VideoThis pagespeech to video lipsyncStandard50720p

    Specs

    Qualities
    480p580p720p
    Max resolution
    720p

    Inputs

    Starting image

    Required — you must upload a starting image.

    Release

    Wan 2.2 Speech to Video was released on August 27, 2025released 12 months ago.

    Compare Wan 2.2 Speech to Video

    Side-by-side pricing, resolution and rankings against models buyers weigh it against.

    Other lipsync models

    Use Wan 2.2 Speech to Video inside these tools

    Frequently asked questions

    How much does Wan 2.2 Speech to Video cost on Versely?+

    Wan 2.2 Speech to Video costs 50 credits on Versely. A full job runs 50-2400 credits depending on output resolution.

    What is Wan 2.2 Speech to Video best for?+

    Wan 2.2 Speech to Video is a Wan lipsync model built for audio to lipsync, image to lipsync.

    How many versions of Wan 2.2 Speech to Video are there?+

    Versely runs 2 Wan 2.2 Speech to Video variants — Wan 2.2 Speech to Video (speech to video lipsync, 50 credits); Wan 2.2 Speech Turbo (image to lipsync, 50 credits). They range from 50 to 50 credits.

    What resolution does Wan 2.2 Speech to Video output?+

    Wan 2.2 Speech to Video supports output up to 720p (available qualities: 480p, 580p, 720p).

    Does Wan 2.2 Speech to Video need a reference image or video?+

    Wan 2.2 Speech to Video requires a starting image.

    Try Wan 2.2 Speech to Video inside Versely

    The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.