Google

Lyria 3.5

lyria-3.5

Google's flagship music generation model that first plans the structure of intro, verse, chorus, and so on, then generates a complete song with vocals and lyrics, supports singing in multiple languages, and can be called via the unified HiAPI.ai API

lyria-3.5

Try lyria-3.5

Input

Lyrics

Showcases

View all showcases

Output

audio

Fill in the parameters and run — results show up here.

Pricing

lyria-3.5 per song

Unit Price	$0.090

Positioning Overview

Lyria 3.5 is a model for text-to-music scenarios, callable through the unified HiAPI.ai interface. It can generate a complete song from a music description (genre, instruments, mood, structure), or directly submit lyrics with [Verse] and [Chorus] section markers for sung performance, with optional song length, BPM, title, and random seed. The output is a complete song with vocals, suitable for developers who need to quickly obtain a well-structured finished product, for content scoring, multilingual songs, and creative demo validation.

Core Highlights

Organizes the whole song by section, rather than stitching fragments — before generation it plans the intro, verse, chorus, bridge, and other structures, so the finished product has clear sections and coherent flow.
Either a description or lyrics alone can produce a song — supplying only a music description yields an instrumental or vocal work; supplying only lyrics goes straight into sung generation.
Song length and tempo can be constrained in the request — you can specify a target duration of 1 to 240 seconds and a numeric BPM, making it easy to reserve length according to placement.

Capabilities

Generating a whole song from a text description: use a description of up to 10,000 characters to specify genre, instruments, mood, and structure, and directly obtain a complete track, reducing manual arrangement and editing steps.

Lyrics-driven vocals: submit lyrics containing section markers to generate a song with vocals, and optionally fill in a title, producing a lyrics-and-music demo ready for direct listening.

Controllable duration and tempo: you can request a target duration of 1 to 240 seconds and specify BPM; the actual output duration may deviate from the requested value, so design around ranges rather than exact values.

Random seeds and reproducible attempts: you can pass numeric seeds to organize multiple rounds of generation, but the same settings do not guarantee identical audio output, making it suitable for variant exploration rather than deterministic reproduction.

Audio-only output: returns a finished audio file that can go directly into an asset library or downstream distribution workflow, with no further format conversion needed.

Use Cases

Short-video and podcast scoring for content creators — input a music brief describing atmosphere and rhythm to get background music matching the finished video's length, ready to drop onto the editing timeline.
Lyrics audition demos for music creators — submit lyrics marked with [Verse] and [Chorus] to produce a listenable sung version, used for validating lyrical and melodic ideas and comparing versions.
Custom scoring for advertising and brand content — generate original tracks that fit the visual tone from genre, instrument, and mood descriptions, serving as scoring drafts for campaign assets.
Music prototypes for games and interactive media — use descriptions plus BPM and duration constraints to batch-generate atmospheric segments as early prototypes for level or interface music for team review.

Limitations and Selection Advice

It supports only text and lyrics input and does not accept image guidance; the output is a watermarked audio file, and generation results cannot be cached. A single track lasts from seconds to several minutes, so it is not suitable for cases requiring long continuous scoring or lossless high-fidelity delivery. The actual output duration and audio details are not guaranteed to match the request parameters exactly, and the same seed cannot reproduce the same result. If you need precisely controllable audio editing, stem separation, or deterministic reproduction, evaluate other solutions; this model is better suited to quickly producing structurally complete finished songs.

What's new

View changelog →

New model Added lyria-3.5 API documentation for song generation from a… Sep 11, 2026

Create a generation task

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

Headers

AuthorizationstringRequired

Account API key. Required on every request. Example: Bearer YOUR_HIAPI_API_KEY. Get your API key

Content-TypestringOptional

The request body is always parsed as JSON; when sent, only application/json (optionally with charset) is accepted — any other value returns 415. Example: application/json.

Idempotency-KeystringOptional

Idempotency key, up to 255 bytes. Retries with the same key from the same account create the task only once; replays return the original taskId.

Idempotency key

On network timeouts or client retries, the same key creates the task only once — no double charges (scope: the API key's account). Use a business-unique identifier as the key (e.g. "order-42"); replays return the original taskId, and keys expire 24 hours after the first request. See the Unified Async API overview for the full scenario matrix.

Body

modelstringRequired

Current fixed value: lyria-3.5

routestringOptional

Current fixed value: default

inputobjectRequired

Business parameters for lyria-3.5 and route default — see the parameter table below.

bpmstringOptionalpattern ^[1-9][0-9]*(\.[0-9]+)?$

Optional. Specifies the tempo (BPM) of the generated track, passed as a numeric string with a minimum value of 1.

seedstringOptionalminLength 1pattern ^[0-9]+$

Optional. Random seed, passed as a numeric string; identical settings do not guarantee identical generated audio.

titlestringOptional

Optional. Specifies a title for the generated song.

lengthintegerOptionalmin 1max 240

Optional. Requested audio duration in seconds, ranging from 1 to 240; the actual output duration may differ.

lyricsstringOptionalminLength 1pattern \S

Optional. Lyrics content, which may use section tags such as [Verse] and [Chorus]; at least one of lyrics or music description must be provided.

promptstringOptionalminLength 1maxLength 10000pattern \S

Optional. Music description, used to specify style, instruments, mood, and structure; at least one of music description or lyrics must be provided.

callbackobjectOptional

Terminal-state notification config. When omitted, no callback is delivered — poll the task yourself. See the callback note below.

Callbacks (Webhook)

Provide callback.url when creating a task and HiAPI POSTs to your service once the task reaches a terminal state — no polling needed. The callback payload mirrors the task detail structure; signature verification, delivery retries and idempotency are documented on the Unified Async API overview page.

urlstringRequired

Required when callback is present. A POST is sent to this URL once the task reaches a terminal state; must be a valid http(s) URL.

whenstringOptionalDefault: "final"

Only final is supported today — notified on both success and fail.

Options:final

storagestringOptionalDefault: "temp"

Artifact storage tier: temp (default, retained about 7 days) or persistent (long-term, billed by size). Insufficient balance or exceeding the storage cap silently downgrades to temp; the effective tier is shown in the task detail response.

Options:temppersistent

Request examples

# Submit an async task; returns a taskId immediately (no waiting for generation)
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer $HIAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "lyria-3.5",
  "input": {}
}'

const res = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.HIAPI_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "lyria-3.5",
    input: {}
  }),
});
const task = await res.json();
// { code: 200, message: "success", data: { taskId } }

import os, requests

res = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": f"Bearer {os.environ['HIAPI_API_KEY']}"},
    json={
        "model": "lyria-3.5",
        "input": {}
    },
)
print(res.json())  # { code, message, data: { taskId } }

200 OK

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR"
  }
}

400 Bad Request

{
  "code": 400,
  "message": "invalid request",
  "data": null,
  "error_code": "INVALID_REQUEST"
}

Get task detail

GET https://api.hiapi.ai/v1/tasks/:id

Response fields

taskIdstringRequired

Task ID, always prefixed with tk-hiapi-.

modelstringRequired

Resolved full model name. Tasks submitted with the route parameter return base@route (e.g. gpt-image-2/text-to-image@ext); otherwise identical to the name passed at creation.

routestringOptional

Present only when the task was submitted with an explicit route parameter; echoes the submitted value.

statusstringRequired

Task status.

Status values

queued Queued, not started yet. handling Being processed. archiving Processing finished, artifacts being prepared. success Terminal: completed, artifacts available (output returned). fail Terminal: failed (error returned). After submission, check status: success and fail are terminal, everything else is non-terminal. Poll every 1–3 seconds until terminal. On success, download artifacts from output[].url and transfer them before expireAt; pass storage: "persistent" at creation time when long-term retention is needed.

creatednumberRequired

Task creation time (Unix seconds).

completednumberRequired

Unix seconds when the task reached a terminal state; fixed to 0 while not terminal.

outputarrayOptional

Present only when status == success. Artifact list — always an array; a single task may return multiple types at once (e.g. video + first_frame).

Array [ object ]

Array items

urlstringRequired

Artifact URL, directly downloadable.

typestringRequired

Current possible values: video, image, audio, first_frame, last_frame, thumbnail; more may be added later.

expireAtnumberRequired

Unix seconds until which the artifact remains accessible; download or transfer before it expires.

errorobjectOptional

Present only when status == fail.

codestringRequired

Business error code.

messagestringRequired

Error description.

Response examples

Success

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-01HZTQ8BX2N3GM3YFK4Z9D7VQR",
    "model": "happyhorse-1-0",
    "status": "success",
    "created": 1777282033,
    "completed": 1777282099,
    "output": [
      {
        "url": "https://cdn.hiapi.ai/tasks/.../video.mp4",
        "type": "video",
        "expireAt": 1777886899
      }
    ]
  }
}

Processing (non-terminal)

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "archiving",
    "created": 1777282033,
    "completed": 0
  }
}

Failed

{
  "code": 200,
  "message": "success",
  "data": {
    "taskId": "tk-hiapi-...",
    "model": "happyhorse-1-0",
    "status": "fail",
    "created": 1777282033,
    "completed": 1777282099,
    "error": {
      "code": "TASK_FAILED",
      "message": "task failed"
    }
  }
}