OmniHuman 1.5 is an audio-driven video model for character narration: starting with a single character photo and a voice recording, it makes static images speak while coordinating lip movements, expressions, and head-and-shoulder movements. It is suitable for product explanations, course introductions, and brand broadcasts. You can adjust emotion and style through prompts, and use a subject mask to specify the appearing person in multi-person photos.
Clarify capacity, inputs and outputs, and invocation methods before selecting a model.
The above are this platform's asset requirements and invocation methods; the recommended audio duration does not represent the model's native limit.
Learn what omnihuman-1.5 can bring to your work.
OmniHuman 1.5 does more than animate the mouth in a photo; it also coordinates expressions and head and shoulder movements with the rhythm of speech. The creative focus is how the character presents the content, making it suitable for narration videos that require a consistent presenter. When preparing audio, first determine pauses, emphasis, and the overall delivery tone.
In addition to photos and voice, you can use prompts to describe emotions such as gentleness, calmness, and naturalness, as well as request subtle head movements or stable performance. This guides the character's performance style and is suitable for creating course explanations, brand broadcasts, and warm content separately, rather than replacing the lines in the audio.
Use a clear front-facing portrait as the visual foundation, without preparing multi-angle modeling assets in advance. Multi-person photos can be paired with a subject mask to specify the driven subject; after generation, you receive a video address to continue downloading, editing, or adding to product pages, allowing character narration to integrate into existing content production workflows.
Start with specific tasks to identify where the model can be effective.
Turn product updates into voiceovers, pair them with a fixed presenter photo, and generate spoken video clips introducing new features. Then combine them with screen recordings, subtitles, and key annotations to deliver videos for help centers or new-user onboarding, with the person handling narration and the screen recording demonstrating actual operations.
Record course openings, knowledge-point overviews, or training reminders as audio, pair them with instructor photos, and generate chapter-based digital human presentations. Using the same image maintains visual continuity across the course; when formulas, charts, or steps are involved, add courseware visuals in post-production rather than having the person present all information.
Prepare different audio tracks for event announcements, product introductions, or frequently asked questions, and use the same brand persona to generate separate videos. Deliverables can further include product footage, subtitles, and end cards; reusing photos can reduce repeated filming, but each piece of content should still be checked to ensure expressions, lip movements, and audio match.
Choose based on task complexity, input materials, and expected results.
If you already have usable photos of a person and finished voiceover audio, and the goal is to have the person speak directly to the audience, OmniHuman 1.5's single-image audio workflow is straightforward. It is better suited to performances organized around sound rather than building complex narratives from text. Choose 1.5 based on presentation needs and sample results; there is no need to interpret the version number as a comprehensive improvement for every task.
For character explanations, course hosting, and brand announcements, consider OmniHuman 1.5 first; if the focus is on large movements, character blocking, scene changes, or precisely recreating a movement, consider animation or video models that support the corresponding controls. For presentation tasks, first test photos, audio, and prompts with short clips before producing complete content.
From a small-scale task to formal integration.
Define the goal, required inputs, and output requirements, and start with real business examples.
Open the trial page, confirm the parameters supported by this entry point, then submit a small-scale task to review the results.
Keep the complete model ID, use the request format specified in the documentation, and confirm billing rules on the Pricing page.
Before official use, understand the output quality and scope of capabilities.
Answers to common questions about using omnihuman-1.5.
This workflow requires a character image and driving audio; text alone cannot replace these two assets. You can first record or create the script as an mp3/wav, then submit the audio URL. The prompt is used to adjust expressions, emotion, and style; it does not directly read the lines aloud.
It is recommended to use a clear, front-facing portrait with good lighting and no obstructions, with the person taking up an appropriate portion of the frame. The photo needs a publicly accessible URL. Before formal production, you can test the photo with a short audio clip to check lip sync, expressions, and head-and-shoulder movement, then continue using the asset.
You can submit an array of subject mask URLs through mask_url to specify the person to be driven in a multi-person photo; even if there is only one mask URL, it should still be submitted as an array. You should first identify the target and prepare the corresponding mask. This feature is for subject selection and should not be understood as allowing multiple characters to speak separately or complete a multi-person conversation in a single request.
The voice itself provides speaking speed, pauses, and delivery rhythm, while the prompt can add requirements such as gentle, calm, natural, or slight head movements. It is recommended to keep the voice-over and prompt consistent, avoiding an impassioned voice with text requesting calmness; the final performance still needs to be checked through the generated video.
Submit image_url and audio_url to POST /dreamina/videos, and specify omnihuman-1.5. Results can be obtained synchronously for short tasks; for longer tasks, you can use callback_url, or set async:true and then query /dreamina/tasks. After completion, read video_url and save it.
Model information · Updated: 2026-10-01. For calling parameters and billing rules, see the API and pricing sections.
Start with a clear goal and assess whether it suits your work based on actual results.
