The voice you choose
Pick your character’s voice from 30 voices, deep or bright, calm or energetic. Each voice can be heard in the tool before you create, with a French and an English preview.
Video model · Google
Gemini Omni 1.1 — Characters who speak, in the voice you choose.
Gemini Omni 1.1 is the Gemini Omni version Google introduced on August 27, 2026. On Deepnia you pick your characters’ voice from 30 voices, write their lines in the prompt, then create a 4, 6, 8 or 10 s clip at 720p or 1080p, 9:16 or 16:9, with sound. Up to 7 reference images guide a face, a product or a setting.
- 4, 6, 8 or 10 s
- 720p or 1080p
- 30 voices to choose
- 7 reference images
- Sound included
The video tool opens with Gemini Omni 1.1 already selected. The exact cost shows before every creation; you sign up when you generate.
- A prompt with the lines
- One of 30 voices, and up to 7 images
- A 4–10 s talking clip
At a glance
- Maker
- Voices
- 30 voices to choose (Kore by default)
- Length
- 4, 6, 8 or 10 s (8 s by default)
- Resolution
- 720p, 1080p (720p by default)
- Aspect ratios
- 9:16, 16:9
- References
- Up to 7 images
What Gemini Omni 1.1 does best
Characters who speak
Put the line in quotation marks in the prompt: the character says it in the chosen voice, lips moving, with the scene’s ambience around.
Several images, one video
Add up to 7 reference images: a presenter’s face, a product, an outfit, a setting. Say in the prompt what each image is for.
Sound with the picture
Every video comes with its own sound, with nothing to switch on: the character’s voice, the ambience and the sounds of the scene.
Ready for social and the web
9:16 and 16:9 at 720p or 1080p: vertical for Reels, TikTok and Shorts, horizontal for YouTube and your website.
Timing you direct
Split the scene with time markers (“[0-3s] … [3-6s] …”) to place each action and each line at the right moment: Google documents this syntax in its guide.
How to use Gemini Omni 1.1 on Deepnia
Open the video tool
The “Try Gemini Omni 1.1” button opens Deepnia’s video tool with the model already selected.
Choose the voice
Listen to the voices and pick your character’s; Kore is the default.
Add your images if you need them
Attach up to 7 photos from your device or your Deepnia library (10 MB per image). Without images, the video starts from text alone.
Write the scene and generate
Describe the scene, put the line in quotation marks, choose the length, resolution and aspect ratio, check the cost shown, then create.
Gemini Omni 1.1 on Deepnia: what you can set
- Inputs
- Text only, or text plus 1 to 7 reference images
- Voices
- 30 voices, Kore by default, with a French and an English preview
- Length
- 4, 6, 8 or 10 s (8 s by default)
- Resolution
- 720p, 1080p (720p by default)
- Aspect ratios
- 9:16, 16:9
- References
- Up to 7 images of up to 10 MB, from your device or Deepnia library
- Sound
- Generated with the video: the chosen voice and the scene’s ambience
- Prompt
- Required, up to 5,000 characters
Prompt ideas to try
Copy a prompt, open the tool and adapt it to your project.
Product presentation to camera
- 9:16
- 8 s
- 1080p
- Voice Kore
- 1 product photo
A young woman holds the bottle from the attached image up to the camera, in a bright bathroom. She smiles and says: "Three drops in the morning, and your skin stays soft all day." Static shot, soft light, phone-video style.
A fitness coach’s tip
- 16:9
- 10 s
- 720p
- Voice Charon
- Text only
A fitness coach in a bright gym looks at the camera and says calmly: "Before you run, take two minutes to warm up. Your knees will thank you." He then shows a warm-up move. Medium shot, steady camera.
Event announcement
- 9:16
- 6 s
- 1080p
- Voice Puck
- Text only
An energetic host on a street hung with string lights calls out to the camera: "Saturday, the big neighborhood party, see you from 6 pm!" He points down the street behind him, where people are setting up stalls. Handheld camera, joyful mood.
Hotel welcome
- 16:9
- 8 s
- 1080p
- Voice Sulafat
- 1 lobby photo
In the hotel lobby from the attached image, a receptionist welcomes the viewer in a warm voice: "Welcome! Your sea-view room is ready for you." The camera slowly moves toward her. Natural morning light.
A recipe at the market
- 9:16
- 10 s
- 720p
- Voice Aoede
- Text only
A smiling cook in the middle of a colorful market in Nairobi holds a steaming bowl of stew and says: "The secret is to let it simmer slowly, no rush." Around her, vegetable stalls and the sounds of the market. Close-up, morning light.
A bookshop’s message
- 16:9
- 6 s
- 720p
- Voice Charon
- Text only
A bookseller in his fifties, between two shelves, sets a book on the counter and says in a calm voice: "Every week, a new favorite is waiting for you here." Warm light, static shot, quiet atmosphere.
Tips for better results
- Put each line in quotation marks and say who says it: the model then knows who should speak.
- Have one character speak per clip: the chosen voice is theirs.
- Keep lines short: one or two sentences fit well in 8 seconds.
- Pick a voice that fits the character (age, energy, tone) and listen to its preview before you create.
- To keep the same face, attach the character’s photo as a reference and describe them with the same words from clip to clip.
Good to know
- For a longer video, create several 10-second clips with the same voice and face, then join them in your editor.
- Pick 9:16 for Reels, TikTok and Shorts, and 16:9 for YouTube and the web.
- Validate the idea at 720p and 4 s, then switch to 1080p for the final cut.
- Use images you have the rights to, especially for a real person’s face.
Gemini Omni 1.1 or another model?
Deepnia’s other video models, to pick the right one for your project.
| Model | Length | Resolution | Aspect ratios | Best for |
|---|---|---|---|---|
| Gemini Omni 1.1This model | 4, 6, 8 or 10 s | 720p–1080p | 9:16 · 16:9 | Characters who speak, in the voice you choose. |
| Gemini Omni | 4, 6, 8 or 10 s | 720p–4K | 9:16 · 16:9 | Clips up to 4K, with speech, music and sound effects. |
| Seedance 2.5 | 4–30 s | 480p–720p | 16:9 · 9:16 · 1:1 · 3:4 · 4:3 · 21:9 | Videos up to 30 s with sound and image and video references. |
| Veo | 8 s | Set by the mode | 9:16 · 16:9 | 8 s clips with sound, in three quality levels. |
| Kling 3.0 | 3–15 s | Set by the mode | 9:16 · 1:1 · 16:9 | A 5-shot editor and persistent characters. |
| Grok Video | 6–30 s | 480p–720p | 9:16 · 1:1 · 16:9 · 2:3 · 3:2 | 6–30 s videos, quick to iterate. |
Frequently asked questions
What is Gemini Omni 1.1?
A version of Google’s Gemini Omni video model family, introduced on August 27, 2026. On Deepnia it creates 4, 6, 8 or 10 s clips where your characters speak in one of 30 voices.
How do I choose my character’s voice?
In the video tool, pick from 30 voices after listening to their French or English preview. Kore is the default.
How do I make a character speak?
Put the line in quotation marks in the prompt and say who speaks and in what tone. The character says it in the chosen voice.
What length and resolution?
4, 6, 8 or 10 seconds, 8 seconds by default, at 720p or 1080p (720p by default), 9:16 or 16:9.
Can I start from my own photos?
Yes, up to 7 images from your device or your Deepnia library, 10 MB each: a presenter’s face, a product, a setting. Say in the prompt what each image is for.
Do the videos have sound?
Yes. Every video is generated with its own sound, with nothing to switch on: the character’s voice and the scene’s ambience.
Gemini Omni or Gemini Omni 1.1: which one should I use?
Gemini Omni 1.1 to choose your characters’ voice from 30. Gemini Omni to go up to 4K, with speech, music and sound effects.
Ready to try Gemini Omni 1.1?
The video tool opens with Gemini Omni 1.1 already selected. The exact cost shows before every creation; you sign up when you generate.