Maestro is a video production service centered on an AI director. After you describe the topic, audience, and communication goals, it organizes the script, visuals, voice-over, music, subtitles, and rendering to turn your idea into a complete video. It is suitable for educational explainers, product promotion, and content production in different languages, and can also incorporate image, video, and audio assets to continue editing or extending existing projects.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
api.acedata.cloudInput parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
The above are the creation and API specifications for the Maestro video production entry point. The target duration does not equal the exact final video duration. All scenes and languages are billed uniformly based on actual delivered seconds × 0.7 credits.
Maestro does more than generate visuals: it connects topics, scripts, narration, music, subtitles, and editing into a production workflow. Prompts can clearly specify the audience, what needs to be explained, how the opening should capture attention, and how the ending should conclude, keeping creation focused on communication goals and making it suitable for launching production directly from a content brief.
Use langs to specify one finished video language. When you need different versions in Chinese, English, Japanese, or other languages, create separate tasks and state the audience and communication requirements for each in the prompt.
Once a video is finished, you do not need to start from scratch every time. remix preserves the theme while adjusting the presentation, edit is for localized changes such as titles, voice-over, or color palettes, and extend is for expanding content. Provide a historical task ID and clear modification requirements to start a new iteration task and progressively refine the same video project.
Enter a concept, tutorial key points, or organized article content, specify the audience's knowledge level and the conclusions you want to retain, then choose narrated to create an explainer video. Deliverables include visuals, narration, and subtitles, making it suitable for turning text content into easy-to-watch shorts; key terms and required information should be specified in the prompt.
Attach reference materials such as product images and logos, describe the selling points, audience, and desired visual feel, then choose a landscape, portrait, or square aspect ratio. Use presets such as modern and luxury to shape the overall look, and pair them with a narration voice; after the video is completed, continue revising the title or voice-over to create different promotional expressions.
When adding subtitles to existing footage, use captions and submit the source video URL; when cross-language distribution is needed, select the target language in langs. The former focuses on processing existing videos, while the latter focuses on creating content separately for each target language, and they can be used respectively for asset organization and multi-region release of product introductions.
If the task requires not only visuals but also a script, voice-over, music, and subtitles, Maestro's director-style workflow is better aligned with complete delivery goals. Rather than making requests only around individual visuals, prioritize describing the content structure and audience expectations here. Use generate for new projects; for projects already created, choose an action based on whether you want to reinterpret, make local edits, or continue the content.
Choose narrated for explainer content, captions for adding subtitles to existing videos, avatar for talking-head videos, and drama for character dialogue stories. The type determines the form of expression, style adjusts the visual look, and voice adjusts the narration voice; do not treat all three as the same type of control. If you want the system to organize the format on its own, keep auto and clearly describe the creative goal.
Specify the audience, topic, structure, duration, and style in prompt; provide assets through file_urls. captions requires a source video, and avatar requires a portrait.
Specify scenario, aspect, and target duration for /maestro/videos; langs can specify only one language at a time. To modify an existing project, use remix/edit/extend with ref_task_id.
Save task_id and query /maestro/tasks, then wait for final success; check the script, voice-over, subtitles, visuals, and volume separately, and do not mistake task acceptance for completed video delivery.
Create a 30-second explainer for beginners on “What is a vector database”: first explain its purpose, then use finding similar images as an example, and finish with a memorable takeaway, with Chinese voiceover and captions, in a clean modern visual style.
Use narrated or auto, focusing on validating script facts, captions, voiceover, and asset transitions; select one language each time, and review the completed video after it is finished.
Maestro is designed to organize complete video production, including not only visuals but also scripts, voiceovers, music, subtitles, editing, and rendering. Prompts should describe the content purpose and presentation structure, rather than just the appearance of shots; it is better suited for creative tasks that need to progress from a brief to a finished video.
Put the media URLs in file_urls, and explain the purpose of each asset in the prompt, for example, product images for display, logos for brand recognition, and videos for subtitle processing. You can submit up to 20 items; when selecting captions, provide a source video, and when selecting avatar, provide a portrait.
Each task can specify only one language, with Chinese as the default. If you need finished videos in other languages, create separate tasks and specify the corresponding creative requirements.
To keep the theme but present it differently, choose remix; to change local content such as titles, voiceovers, or colors, choose edit; to continue expanding the original content, choose extend. All three require ref_task_id, and you should state the modification goal in the prompt; a new task ID will then be returned.
After calling POST /maestro/videos, first obtain the task_id, then use POST /maestro/tasks to check progress and results. Tasks go through planning and production stages, and the finished video is available upon success; applications should distinguish between submission successful, in production, completed, and failed states.
Choose a development approach or application suited to this model and follow its setup guide.
