Microsoft Speech

Example Usage

D-ID provides Microsoft Azure Cognitive Services integration to generate text to speech

"provider": {
	"type": "microsoft",
	"voice_id": "en-GB-AbbiNeural"
}

"provider": {
  "type": "microsoft",
  "voice_id": "en-US-JennyNeural",
  "voice_config": {
  	"style": "Cheerful"
  }
}

"provider": {
  "type": "microsoft",
  "voice_id": "en-US-JennyNeural",
  "voice_config": {
  	"rate": "1.2"
  }
}

Available Voices

Go to Microsoft Voice Gallery above, and:

1. Select any voice from the voice gallery
2. Click on the "Sample code" tab on the right
3. Copy the voice name: config.SpeechSynthesisVoiceName ="en-GB-AbbiNeural"
4. Use this string en-GB-AbbiNeural in the voice_id field

Voice Config

Style: The style parameter selects the speaking style of the voice, for example Cheerful. Available styles change between voices.

Speed: The rate parameter controls how fast the voice speaks. The value is relative to 1 (normal speed), 0.5 being half speed and 2 being twice as fast. Default value: 1. Another option is one of x-slow, slow, medium, fast, x-fast.

Pitch: The pitch parameter changes the pitch of the voice, for example +2st (two semitones up), a value in Hz, for example +50Hz, or one of x-low, low, medium, high, x-high.

Adding Pauses

Adding pauses to the audio generated by Microsoft TTS is possible using the SSML (Speech Synthesis Markup Language) with the syntax and the examples below. Adding <break time=\"5000ms\"/> will create an exact and natural pause in the speech for 5 seconds. It is not just added silence between words, but the AI has an actual understanding of this syntax and will add a natural pause.

{
   "script":{
      "type":"text",
      "ssml": true,
      "input": "Enjoy the 5000 milliseconds break <break time=\"5000ms\"/> generated by Microsoft",
      "provider":{
         "type":"microsoft",
         "voice_id":"en-US-JennyNeural"
      }
   }
}

Fully Silent (Idle) Video Example

A fully silent (idle) video is a video generated using /talks endpoint, without any words. The avatar is silent and doesn't pronounce anything. Head movements, gentle smiles, and eye-blinking still persist, which makes the silent video a great asset to use in your projects.

To create a silent video of 15 seconds (recommended), simply create a /talk with Microsoft TTS provider and 3 consequence silent breaks (5 seconds each). In the request example below, "ssml": **true** indicates that the special markup language will be used, and <break time=\"5000ms\"/> is a 5-second pause of silence. Three pauses of 5 seconds each have been added to generate a 15-second video.

Full JSON example of generating a Silent (Idle) video:

{
    "source_url": "https://create-images-results.d-id.com/DefaultPresenters/Emma_f/image.jpeg",
    "driver_url": "bank://lively/driver-06",
    "script": {
        "type": "text",
        "ssml": true,
        "input": "<break time=\"5000ms\"/><break time=\"5000ms\"/><break time=\"5000ms\"/>",
        "provider": {
            "type": "microsoft",
            "voice_id": "en-US-JennyNeural"
        }
    },
    "config": {
        "fluent": true
    }
}

Best Practices to follow when generating a silent video:

Support