Speech - Unifically

Turn text into expressive spoken audio. Give Suno the exact words to say, or describe what you want and let Suno write the script. Each request returns a pair of speech clips.

Model

suno-ai/speech

Two ways to use it

Your script: send text with the exact words. You can steer the delivery with tone, turn background music on or off, and choose how much the delivery may vary.
Suno writes it: send description (for example, “a 20 second weather report for a sunny day”). Suno writes and speaks the script.

Send exactly one of text or description.

Parameters

Parameter	Type	Required	Description
`text`	string	One of `text` / `description`	The exact words to speak
`description`	string	One of `text` / `description`	What the speech should be about; Suno writes the script
`tone`	string	No	Delivery style: tone, pacing, mood, setting. For example `warm, confident narrator, medium pace`. Only with `text`
`title`	string	No	Title for the clips. Suno names them when empty
`vocal_gender`	string	No	Speaker voice: `m` or `f`
`background_music`	boolean	No	Lay music under the voice. Default: `true`. Only with `text`
`variety`	integer	No	How much the delivery may vary, `0`–`4`: `1` Normal, `2` High, `3` Extra, `4` Max. Default: `1`. Only with `text`

Examples

Your script:

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "suno-ai/speech",
    "input": {
      "text": "Welcome back to the show. Today we are talking about the future of sound.",
      "tone": "warm podcast host, relaxed pace",
      "vocal_gender": "f",
      "background_music": false
    }
  }'

Let Suno write the script:

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "suno-ai/speech",
    "input": {
      "description": "A 20 second radio ad for a neighborhood coffee shop"
    }
  }'

Response

{
  "code": 200,
  "success": true,
  "data": {
    "task_id": "abc123def456",
    "status": "processing"
  }
}

The completed task returns clips, the same shape as Music Generation. Each clip’s audio_url is an MP3.

Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.

​Model

​Two ways to use it

​Parameters

​Examples

​Response

Model

Two ways to use it

Parameters

Examples

Response