Avatar workflow / Evidence guide
How to make a talking photo with AI: image, voice and a checked example
A talking-photo generator animates a still image to match supplied speech. Donatello Avatar takes an image and audio, rather than inventing a complete script-to-video sequence. This guide follows a fictional presenter example whose original MP4 and inputs are available to inspect.
Key takeaway
Use one clear, authorized face and clean speech. Select Fast or Quality explicitly, check the duration-based quote, then review the mouth, identity and audio before downloading. Free access and commercial use have the conditions explained below.01 / Avatar workflow
1. Prepare a portrait and a short voice track
Use your own photo, an original synthetic character or a portrait you have permission to animate. A frontal or gently turned face with a visible mouth gives you fewer things to troubleshoot than a distant face, hand-covered lips or a strong profile.
Write a short message and record it, use audio you own, or create synthetic narration in Donatello Voice. You can also use Create audio inside the Avatar editor; that voice-generation step has its own quote. Keep music and overlapping voices out of an initial test.
02 / Avatar workflow
2. Create the talking photo in Avatar
Open Avatar and choose one character. Upload the image and audio, or select available files from your Donatello library. Choose Quality or the lower-cost Fast option. The audio determines duration; the quote rounds up to whole seconds with a three-second minimum.
Confirm that you have permission for the inputs, review the displayed cost and start generation. Fast is not a switch that enables free processing. If you need a long edited sequence with narration, captions and multiple scenes, use Full Video Creator instead.
03 / Avatar workflow
3. Inspect a real talking-photo example
This fictional botanical presenter was generated in Quality from an original synthetic portrait and English narration. The original output is 10.419 seconds at 1942 × 1068 pixels: an upscale targeting 1080p, not native 1080p. The Avatar step used 1,485 credits; image and voice creation were separate.
The spoken text is: “A tiny seed can change an entire landscape. Give it light, water, and a little patience. Every garden begins with one small decision to grow.” This is a first-party, credit-funded example, not an independent quality benchmark or proof of Relax availability.
04 / Avatar workflow
4. Review before you publish
Watch the whole clip with sound. Check the mouth at the start and end of sentences, teeth, blinking, head shape and whether the words remain understandable. A plausible still frame does not prove accurate lip-sync. If something looks wrong, simplify the input or create a new test rather than publishing it unreviewed.
Download the MP4 before private files expire after 72 hours. Donatello does not add a visible branding watermark, but source-file marks remain. Label synthetic presenters where necessary and do not present them as real customer testimonials.
05 / Avatar workflow
Free access, costs and commercial use
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.
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.
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.
Verification
Sources and current facts
Product conditions can change. Donatello's dated Product Facts and binding Terms take precedence over this explanatory article if a material detail is updated.