Donatello

Donatello Avatar / Image + audio → video

Create a talking AI avatar.

Turn an original character, a licensed portrait or your own photo into a talking video. Add recorded speech or narration made with Donatello Voice, then choose a single speaker or a two-person dialogue.

Free access · No subscription required · Commercial use under the Terms

Create an avatar →See examples ↓Leer en español

Donatello Avatar

Make one image speak.

Sign in to upload private source files and keep the generated video in your 72-hour library.

Sign in to create

From a photo to a talking avatar

01

Prepare a clear face

Use a sharp, front-facing portrait with an unobstructed mouth. For dialogue, show two clearly separated people.

02

Add your audio

Upload an authorized recording or create narration in Donatello Voice. With two speakers, assign left and right audio and choose the speaking order.

03

Review and create

Check duration, price and input permissions. Generate the video, review mouth movement and audio, and download it before the 72-hour expiry.

Examples and quality you can inspect

Inspect original videos, generation conditions and limitations in the Verified Gallery. A credit-funded demonstration does not prove the availability of subsidized generation.

Free-access AI avatar generator: clear conditions

Start without a subscription using free welcome or earned credits; paid credits are optional. If credits are insufficient and a fresh check confirms no surveys are available, eligible accounts may receive automatic lower-priority processing. It requires available free funds and must fit the existing daily subsidy limit. It does not promise unlimited free avatars of any duration.

Free-processing budget and waiting time

The current subsidy limit is $0.25 per user per day across eligible generation. Fast reserves $0.020 per billed second plus $0.01 of upscale rounding headroom: a 3-second job reserves $0.07 and a 12-second job reserves $0.25. Quality reserves $0.065 per billed second plus the same headroom: 3 seconds reserve $0.205, while 4 seconds exceed the cap. These are admission estimates, not extra charges to the user. Prior usage reduces availability; remaining credits can fund part of a job. Eligibility and available funds are still required. The minimum wait remains 180 minutes; queues can add time. Selecting Fast does not activate or bypass free-processing eligibility.

Duration-based pricing

Fast: 45 credits per billed second. Quality: 135 credits per billed second. Round audio duration up to whole seconds with a 3-second minimum. A 10-second avatar costs 450 credits in Fast or 1,350 in Quality; 30 seconds cost 1,350 or 4,050 credits respectively. Both include the 1080p-target upscale. Quality remains the default; Fast is an explicit lower-cost choice, not a free-processing switch. Creating the input image or voice separately has its own quote. The editor confirms the current price before submission.

See all pricing →

Commercial-use talking videos without an added watermark

Donatello permits commercial and monetized use of Avatar outputs under the Terms, including client explainers, lessons and marketing. You must have permission for the image, audio, voice and likeness, and comply with applicable provider terms. This is not a guarantee of copyright, exclusivity or freedom from third-party claims. Do not impersonate someone or present a synthetic presenter as a real testimonial.

Donatello does not add a visible branding watermark to the exported MP4. This does not remove marks already present in your source files or waive required disclosures and third-party attribution.

Terms of useProvider commercial-use policyModel license

Resolution, duration and files

One or two visible speakers. Up to 10 minutes of combined sequential audio, or the longer track for simultaneous dialogue. Quality uses native 720p generation; Fast uses the lower-cost provider route. Both include a 1080p-target upscale, not native 1080p. Exact dimensions depend on source framing. The public gallery identifies each example’s mode, language and measured dimensions; the same-input Fast/Quality comparison is not an independent quality ranking. Private input and output files expire after 72 hours. Download the MP4 to keep it.

Create your imageCreate your narrationCreate a multi-scene video

Frequently asked questions

Is the AI avatar generator free and unlimited?

You can use free welcome or earned credits without a subscription. Automatic free fallback is conditional on insufficient credits, confirmed no surveys, eligibility, the daily subsidy limit and available funds. There is no promise of unlimited subsidized avatars or free 10-minute videos.

Can I use my talking avatar commercially?

Yes, under the Terms and applicable provider conditions, provided you hold the necessary image, audio, voice and likeness permissions. Commercial permission does not guarantee copyright, exclusivity or non-infringement.

Does the video have a Donatello watermark?

Donatello does not add a visible branding watermark to the exported MP4. This does not remove marks already present in your source files or waive required disclosures and third-party attribution.

Can I start from text?

Avatar animates an image using audio. First create narration in Donatello Voice to turn text into speech. Full Video Creator is the separate workflow for narrated multi-scene videos.

Can two characters talk in the same video?

Yes. Supply one image containing two visible people and separate left and right audio tracks. Choose left then right, right then left, or simultaneous speech. Clear separation and clean audio improve results.

How can I improve lip-sync quality?

Use a sharp portrait, a visible mouth and a clean single-voice recording without loud background music. Review before publishing: fast speech, profiles, occlusion and overlapping voices can reduce accuracy.

Practical guides and a real comparison

English and Spanish guides with original files, settings and test limitations.

Avatar facts reviewed: 2026-11-07. Product Facts