Lyria 3.5 API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model	lyria-3.5
Input	Description or lyrics
Output	Audio

Generate a song from a musical description and optional lyrics, with a title, tempo guidance, and a seed.

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "lyria-3.5",
  "input": {
    "bpm": "90",
    "length": 30,
    "prompt": "Warm instrumental indie folk, fingerpicked acoustic guitar, soft brushed drums, quiet morning."
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "lyria-3.5",
  "input": {
    "bpm": "90",
    "length": 30,
    "prompt": "Warm instrumental indie folk, fingerpicked acoustic guitar, soft brushed drums, quiet morning."
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "lyria-3.5",
  "input": {
    "bpm": "90",
    "length": 30,
    "prompt": "Warm instrumental indie folk, fingerpicked acoustic guitar, soft brushed drums, quiet morning."
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

example lyria-3.5

input object required

prompt string optional

Describe genre, instruments, mood, vocals, and song structure. Provide prompt or lyrics.

lyrics string optional

Lyrics, one line per phrase. Basic section tags are [Intro], [Verse], [Chorus], [Bridge], and [Outro]. Put each tag on its own line, followed by the lyrics. Number repeated verses as [Verse 1] and [Verse 2]; see the section-tag table below.

title string optional

Title of the generated song.

bpm string optional

Tempo guidance supplied as a numeric string, such as "90".

length integer optional

Requested duration in seconds, an integer from 1 to 240. Guides the song length; actual audio duration may vary. Omit to leave duration unspecified.

seed string optional

Random seed supplied as text; identical audio is not guaranteed.

callback object optional

url string required

when enum optional

default final enum: final

Lyrics section tags

Place these tags in the lyrics to guide the arrangement. A song does not need to use every tag.

Tag	Section	Usage
[Intro]	Intro	`Place at the beginning.`
[Verse]	Verse	`Follow with verse lyrics; repeated verses can be numbered [Verse 1], [Verse 2].`
[Chorus]	Chorus	`Follow with the recurring main section.`
[Bridge]	Bridge	`Mark a contrasting connecting section.`
[Outro]	Outro	`Place at the ending.`

Example requests

Carry the Morning

Create an acoustic pop song with custom lyrics.

Request body

{
  "model": "lyria-3.5",
  "input": {
    "bpm": "90",
    "length": 30,
    "prompt": "Warm instrumental indie folk, fingerpicked acoustic guitar, soft brushed drums, quiet morning."
  }
}

Getting the result

Read the task ID from data.taskId after creation.
Use GET /v1/tasks/{taskId} until data.status is success or fail.
On success, find the type=audio item in data.output and retrieve the audio from url.

FAQ

How do I use my own lyrics?

Put your words in lyrics and describe genre, instruments, and vocals in prompt. Use the section tags above to guide the arrangement.

How do I request an instrumental?

Ask for “instrumental only, no vocals” in prompt, then describe the instruments and mood. Leave lyrics empty.

Does this endpoint accept images?

This endpoint accepts a music description and lyrics; it does not expose an image input.

Next steps

Playground