Basic
Good for testing ideas and everyday social clips.
14 tokens per second, minimum 100 tokens
Available on any account with enough tokens.
Add a photo with a clear face, then write a script, upload audio or record your voice. Gulf Picasso syncs the lips to the words and delivers a talking video, with no camera and no studio.
A real example made on Gulf Picasso with Pro quality: one photo and one audio file in Tunisian dialect. Turn the sound on to hear it.

أخطر حاجة تنجم تسرّع تجاعيد البشرة موش العمر. برشا ناس يركزوا على الكريمات، أما ينساو أهم حاجة داخل الجسم. الدراسات تقول إنه ستريس ينجم يستهلك مضادات الأكسدة داخل جسمك.A speaking face holds attention longer than a still image, and you don't need to film anyone.
Have a character present your offer directly to the viewer, in your market's language.
Give your mascot or cartoon character a voice for campaigns and social posts.
Make short talking clips for Instagram, Snapchat and TikTok without appearing on camera.
Turn lessons, staff training and awareness messages into a presenter that explains them.
Use a character you generated as a recurring presenter for your account.
Send a spoken greeting from a character for Ramadan, Eid and National Day.
Use whichever suits you. Clips can be up to 30 seconds long.
Type the words and pick a voice. About 200 characters makes around 30 seconds of speech.
Use your own voice-over as an audio file of up to 9 MB and 30 seconds.
Record directly in the browser, up to 30 seconds, and the character speaks with your voice.
Pick the voice in the generator and hear it before you use it.
Choose Arabic voices by accent, including Gulf, Egyptian and Levantine, alongside Modern Standard Arabic.
Switch to English voices when your audience needs them.
On Studio and Ultra plans, clone your own voice for a one-time 100 tokens and keep up to 2 clones.
You pay per second of video, with a minimum per video.
Good for testing ideas and everyday social clips.
14 tokens per second, minimum 100 tokens
Available on any account with enough tokens.
Higher quality for ads and videos that represent your brand.
65 tokens per second, minimum 200 tokens
For Standard, Studio and Ultra subscribers.
It's fast for spoken content. Some videos still need a real shoot.
Three things make the biggest difference.
Pick a photo where the face is visible, facing the camera and well lit.
One idea in one clip works best. For longer messages, join clips in the video editor.
Choose a voice that fits the character's age and personality, and write the way people speak.
The points count resets to30 pointsevery day, generating an image costs at least one point.
View breakdown
Generate 2 videos at the same time
View breakdown
Generate 5 videos at the same time
View breakdown
Generate 6 videos at the same time
It makes the lips of a person or character in a photo move to match a voice. You add a photo and the audio, and you get a talking video without filming.
Add a photo with a visible face, then write a script, upload audio or record your voice. Choose the quality and generate. The video takes about 5 minutes and also appears in My Assets.
Yes. You can write your script in Arabic and pick an Arabic voice, or upload or record audio in your own dialect.
Up to 30 seconds per clip. For longer content, make several clips and join them in the video editor.
Basic costs 14 tokens per second with a minimum of 100 tokens. Pro costs 65 tokens per second with a minimum of 200 tokens.
The free plan's 30 daily tokens don't reach the 100-token minimum, so you'll need a paid plan. Pro quality requires a Standard, Studio or Ultra subscription.
Yes. Upload or record your voice for any clip. On Studio and Ultra plans you can also clone it for 100 tokens and use it from a script.
Yes. Mascots and illustrated characters work as long as the face is clear.
Only with their permission. Generating videos of public figures isn't allowed.
Add a photo and your words, and get a talking video in minutes.
Make my first talking video