How to complete image/text-to-video - Intelligent Media Services

Configure Timeline parameters for the SubmitMediaProducingJob API operation to produce videos from images, text overlays, and text-to-speech (TTS) audio. For details about all available Timeline parameters, see Timeline configurations.

Usage notes

Intelligent Media Services (IMS) intelligent production supports editing, compositing, effect rendering, and templates for live streams, VOD files, and material files from Object Storage Service (OSS). For more information, see Intelligent production overview.
Produce a video from one or more videos, audio files, images, and subtitle materials by configuring Timeline parameters and calling the SubmitMediaProducingJob operation.
A timeline defines the structure of a video. It consists of tracks, materials, and effects. For more information, see Timeline configurations.
For information about how to use the IMS SDK for audio and video editing, see Preparations.

Voice-over aligned slideshow

Produces a narrated slideshow where each image displays for the duration of its corresponding TTS audio clip. Suitable for webpage-to-video or document-to-video workflows.

The timeline links image clips to TTS audio clips through ReferenceClipId. Each image clip sets ReferenceClipId to the ClipId of a TTS audio clip. IMS automatically adjusts the image duration to match the TTS audio duration.

Output video: 1.mp4

Timeline structure

Track type	Count	Purpose
`VideoTracks`	1 track, 4 image clips	Displays images with text overlays. Each clip references a TTS audio clip through `ReferenceClipId`.
`AudioTracks`	2 tracks	Track 1 (`MainTrack: true`): 4 `AI_TTS` clips that generate voice-over narration. Track 2: background music with `LoopMode: true`.
`SubtitleTracks`	1 track, 1 clip	Displays a persistent title at the top of the video.

Key parameters

Parameter	Value	Description
`ReferenceClipId`	`"speech1"`, `"speech2"`, etc.	Set on each image clip. Links the image to a TTS audio clip so their durations match.
`ClipId`	`"speech1"`, `"speech2"`, etc.	Set on each TTS audio clip. Serves as the reference target for image clips.
`Type`	`"AI_TTS"`	Specifies that this audio clip is generated by text-to-speech.
`Voice`	`"zhichu"`	TTS voice model.
`SpeechRate`	`-200`	TTS speaking speed. Negative values produce slower speech.
`MainTrack`	`true`	Marks the TTS audio track as the primary track for timeline duration.
`LoopMode`	`true`	Loops background music to fill the entire video duration.
`AdaptMode`	`"AutoWrap"`	Automatically wraps text within the specified `TextWidth`.
`EffectColorStyle`	`"CS0004-000005"`	Preset color style applied to subtitle text.

Timeline JSON

{
  "VideoTracks": [{
    "VideoTrackClips": [{
      "ReferenceClipId": "speech1",
      "MediaURL": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/a1.png",
      "Type": "Image",
      "Effects": [{
        "Type": "Text",
        "Content": "Confucius said: \"Is it not a pleasure to learn something and constantly put it into practice? Is it not a delight to have friends from afar? Is it not a gentleman to remain unsoured even though one's merits are unrecognized by others?\"",
        "Alignment": "CenterCenter",
        "FontSize": 55,
        "AdaptMode": "AutoWrap",
        "TextWidth": 0.7,
        "Font": "FZKai-Z03S",
        "FontColor": "#ffffe0",
        "Outline": 2,
        "OutlineColour": "#000000",
        "FontFace": {
          "Bold": true,
          "Italic": false,
          "Underline": false
        }
      }]
    },{
      "ReferenceClipId": "speech2",
      "MediaURL": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/a2.png",
      "Type": "Image",
      "Effects": [{
        "Type": "Text",
        "Content": "Confucius said: \"Isn't it a pleasure to review and practice what you have learned on time? Isn't it happy to have friends from far away? Isn't it a cultured gentleman's merit to remain unsoured even though one is unrecognized by others?\"",
        "Alignment": "CenterCenter",
        "FontSize": 55,
        "AdaptMode": "AutoWrap",
        "TextWidth": 0.7,
        "Font": "FZKai-Z03S",
        "FontColor": "#ffffe0",
        "Outline": 2,
        "OutlineColour": "#000000",
        "FontFace": {
          "Bold": true,
          "Italic": false,
          "Underline": false
        }
      }]
    },{
      "ReferenceClipId": "speech3",
      "MediaURL": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/a3.png",
      "Type": "Image",
      "Effects": [{
        "Type": "Text",
        "Content": "Confucius said: \"If a man keeps cherishing his old knowledge, so as continually to be acquiring new, he may be a teacher of others.\"",
        "Alignment": "CenterCenter",
        "FontSize": 55,
        "AdaptMode": "AutoWrap",
        "TextWidth": 0.7,
        "Font": "FZKai-Z03S",
        "FontColor": "#ffffe0",
        "Outline": 2,
        "OutlineColour": "#000000",
        "FontFace": {
          "Bold": true,
          "Italic": false,
          "Underline": false
        }
      }]
    },{
      "ReferenceClipId": "speech4",
      "MediaURL": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/a4.png",
      "Type": "Image",
      "Effects": [{
        "Type": "Text",
        "Content": "Confucius said: \"If you gain something new when you review your old knowledge, you can become a teacher.\"",
        "Alignment": "CenterCenter",
        "FontSize": 55,
        "AdaptMode": "AutoWrap",
        "TextWidth": 0.7,
        "Font": "FZKai-Z03S",
        "FontColor": "#ffffe0",
        "Outline": 2,
        "OutlineColour": "#000000",
        "FontFace": {
          "Bold": true,
          "Italic": false,
          "Underline": false
        }
      }]
    }]
  }],
  "AudioTracks": [{
    "MainTrack": true,
    "AudioTrackClips": [{
      "ClipId": "speech1",
      "Type": "AI_TTS",
      "Voice": "zhichu",
      "Content": "The Analects, Chapter 12. Confucius said: \"Is it not a pleasure to learn something and constantly put it into practice? Is it not a delight to have friends from afar? Is it not a gentleman to remain unsoured even though one's merits are unrecognized by others? \"",
      "SpeechRate": -200
    },{
      "ClipId": "speech2",
      "Type": "AI_TTS",
      "Voice": "zhichu",
      "Content": "Translation. Confucius said: \"Isn't it a pleasure to review and practice what you have learned on time? Isn't it happy to have friends from far away? Isn't it a cultured gentleman's merit to remain unsoured even though one is unrecognized by others?\"",
      "SpeechRate": -200
    },{
      "ClipId": "speech3",
      "Type": "AI_TTS",
      "Voice": "zhichu",
      "Content": "Confucius said: \"If a man keeps cherishing his old knowledge, so as continually to be acquiring new, he may be a teacher of others.\"",
      "SpeechRate": -200
    },{
      "ClipId": "speech4",
      "Type": "AI_TTS",
      "Voice": "zhichu",
      "Content": "Translation. Confucius said: \"If you gain something new when you review your old knowledge, you can become a teacher.\"",
      "SpeechRate": -200
    }]
  },{
    "AudioTrackClips": [{
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/music/m1.wav",
      "LoopMode": true
    }]
  }],
  "SubtitleTracks":[
    {
      "SubtitleTrackClips": [
        {
          "Type": "Text",
          "Y": 150,
          "Content": "The Analects, Chapter 12",
          "Font": "HappyZcool-2016",
          "Alignment": "TopCenter",
          "EffectColorStyle": "CS0004-000005",
          "AdaptMode": "AutoWrap",
          "FontSize": 70,
          "TextWidth": 900,
          "FontFace": {
            "Bold": false,
            "Italic": false,
            "Underline": false
          }
        }
      ]
    }
  ]
}

Music album from images

Produces a slideshow video with background music, transitions between images, and blurred background fills. Each image displays for a fixed duration. No TTS or text overlays are used.

Output video: 2.mp4

Timeline structure

Track type	Count	Purpose
`VideoTracks`	1 track, 7 image clips	Displays images sequentially. Each clip has a blurred background fill and a random transition.
`AudioTracks`	1 track	Background music with `LoopMode: true` to cover the full video duration.

Key parameters

Parameter	Value	Description
`Duration`	`3`	Each image displays for 3 seconds.
`Type` (effect)	`"Background"`	Adds a blurred background behind images that do not fill the video frame.
`SubType` (background)	`"Blur"`	Applies a blur effect for the background fill.
`Radius`	`0.1`	Blur intensity for the background effect.
`Type` (effect)	`"Transition"`	Adds a transition effect between consecutive clips.
`SubType` (transition)	`"random"`	Applies a randomly selected transition style.
`Duration` (transition)	`0.5`	Transition duration in seconds.
`LoopMode`	`true`	Loops background music to fill the entire video duration.

Timeline JSON

{
  "VideoTracks": [{
    "VideoTrackClips": [{
      "Type": "Image",
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/01.jpg",
      "Duration": 3,
      "Effects": [{
        "Type": "Background",
        "SubType": "Blur",
        "Radius": 0.1
      }, {
        "Type": "Transition",
        "SubType": "random",
        "Duration": 0.5
      }]
    },{
      "Type": "Image",
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/02.jpg",
      "Duration": 3,
      "Effects": [{
        "Type": "Background",
        "SubType": "Blur",
        "Radius": 0.1
      }, {
        "Type": "Transition",
        "SubType": "random",
        "Duration": 0.5
      }]
    },{
      "Type": "Image",
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/03.jpg",
      "Duration": 3,
      "Effects": [{
        "Type": "Background",
        "SubType": "Blur",
        "Radius": 0.1
      }, {
        "Type": "Transition",
        "SubType": "random",
        "Duration": 0.5
      }]
    },{
      "Type": "Image",
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/04.jpg",
      "Duration": 3,
      "Effects": [{
        "Type": "Background",
        "SubType": "Blur",
        "Radius": 0.1
      }, {
        "Type": "Transition",
        "SubType": "random",
        "Duration": 0.5
      }]
    },{
      "Type": "Image",
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/05.jpg",
      "Duration": 3,
      "Effects": [{
        "Type": "Background",
        "SubType": "Blur",
        "Radius": 0.1
      }, {
        "Type": "Transition",
        "SubType": "random",
        "Duration": 0.5
      }]
    },{
      "Type": "Image",
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/06.jpg",
      "Duration": 3,
      "Effects": [{
        "Type": "Background",
        "SubType": "Blur",
        "Radius": 0.1
      }, {
        "Type": "Transition",
        "SubType": "random",
        "Duration": 0.5
      }]
    },{
      "Type": "Image",
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/image/07.jpg",
      "Duration": 3,
      "Effects": [{
        "Type": "Background",
        "SubType": "Blur",
        "Radius": 0.1
      }, {
        "Type": "Transition",
        "SubType": "random",
        "Duration": 0.5
      }]
    }]
  }],
  "AudioTracks": [{
    "AudioTrackClips": [{
      "MediaUrl": "http://ice-document-materials.oss-cn-shanghai.aliyuncs.com/test_media/music/m1.wav",
      "LoopMode": true
    }]
  }]
}

Intelligent Media Services:Create videos from images and text

Usage notes

Voice-over aligned slideshow

Timeline structure

Key parameters

Timeline JSON

Music album from images

Timeline structure

Key parameters

Timeline JSON

References