Introduction
You describe the style in prompt and, if you have them, put the words to sing in lyrics. Suno says v6 is its reliable, precise model, and in our tests it sang a lyric sheet word for word, in order.
Key features
Two takes every time
Each request returns two full versions of the song. They are not clips of one another: they can differ in arrangement and in length, so you can keep the one you like.
Your lyrics, sung as written
An 11-line lyric sheet came back sung line by line in the order we wrote it. Section tags such as [Verse] and [Chorus] shaped the structure without being sung, and the chorus was not repeated unless the lyrics repeated it.
Three ways to handle the words
Bring your own lyrics, let the model write them from prompt (generate_lyrics is on by default), or switch on instrumental for no vocals. Fine controls such as title, vocal_gender, style_weight, weirdness, variety and personas apply when you bring your own lyrics or go instrumental.
Request parameters
| Parameter | Required | Description |
|---|---|---|
audio_weight | No | How strongly a persona's audio shapes the result, from 0 to 1. Songs with vocals only. ≥ 0 · ≤ 1 |
generate_lyrics | No | Let the model write the lyrics from the prompt. Only applies when lyrics is empty and instrumental is off. Default: true |
image_urls | No | Pictures that set the mood; the music takes its feel from them. |
instrumental | No | Music only, no vocals. Default: false |
lyrics | No | Write your own lyrics, or leave it to the model. |
negative_prompt | No | Styles or sounds you don't want in the track. |
persona_id | No | ID of an existing Suno persona to reuse its style or voice. |
persona_model | No | Whether persona_id is a style persona or a voice persona. style_persona · voice_persona |
prompt | Yes | Describe the song: genre, mood, tempo, instruments and voice. With lyrics or an instrumental this is the style (up to 1,000 characters); with no lyrics the model writes the words from it. |
reference_audio_urls | No | Audio to match: a voice, music or a rhythm. |
reference_video_urls | No | A video the music should fit. |
style_weight | No | How closely to follow the style in the prompt, from 0 to 1. ≥ 0 · ≤ 1 |
title | No | Song title (metadata, not sung). Applies with lyrics or an instrumental; otherwise the model names the song. |
variety | No | How different the two versions are from each other: 0 off, 1 normal (the model default), 2 high, 3 extra, 4 max. ≥ 0 · ≤ 4 |
vocal_gender | No | Make a female or male lead vocal more likely. Applies with lyrics. female · male |
weirdness | No | How experimental the song may get, from 0 (conventional) to 1 (unusual). ≥ 0 · ≤ 1 |
Pricing
Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.
| Option | Credits per run | ≈ USD |
|---|---|---|
| Standard | 10.8 | $0.11 |
Each task is rounded up to whole credits, so one run at the lowest tier costs 11 credits per run ($0.11).
For an exact number before you run, send the same body to POST /jobs/quote.
Use cases
Songs you have already written
Poems, toasts, jingles and story songs: keep the text, choose the genre and voice, and compare two versions. Songs ran from about a minute and a half for a short lyric sheet to over two minutes for a full one.
Music that follows a picture or a clip
With generated lyrics you can send up to 5 mood images, one reference video or one reference audio, and the model writes a song around them. For a wordless underscore, switch on instrumental.
Prompt guide & pro tips
Describe the sound, not the artist
Write genre, tempo in bpm, two or three instruments and the kind of voice: “soft neo-soul ballad, 78 bpm, warm female lead vocal, Rhodes piano”.
Tag the sections
Put [Intro], [Verse], [Chorus], [Bridge] and [Outro] on their own rows and repeat the chorus text where you want it to return. More lines make a longer song; there is no duration setting.
API quick start
Call the Suno v6 API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
- Send the request. POST /jobs/createTask with model suno/v6/text-to-audio and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "suno/v6/text-to-audio",
"input": {
"prompt": "Calm ambient pads with a slow rising motif"
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.
Suno v6 API questions
How much does the Suno v6 API cost?
Suno v6 costs 11 credits ($0.11) per run. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.
What is the model name for Suno v6 in the API?
Put suno/v6/text-to-audio for Music in the model field of POST /jobs/createTask.
What does Suno say about v6?
Suno says v6 is reliable, precise and consistently delivers polished music across every genre and style. It launched on 9 September 2026 alongside v6 Wild and v6 Mini.
Will it sing my lyrics exactly?
In our tests with default settings, yes. An 11-line lyric sheet was sung word for word in the order written; section tags like [Chorus] were not sung and the chorus was not repeated on its own.
Am I charged if a request is rejected or fails?
No. The amount held for the request is released in full.
Can I choose who sings?
Partly. Describe the voice in the style brief, such as a confident female lead. With your own lyrics or instrumental on you can also set vocal_gender to female or male; it is a preference, not a guarantee, and we have not measured how often it holds. A duet asked for in a one-sentence idea came back as a solo in our test, so name one voice if it matters.
What are the limits of the Suno v6 API?
Reference images: 5; Reference audio: 1; Reference videos: 1; Prompt length (characters): 3,000. Requests outside these limits are rejected before anything is charged.
Can I try Suno v6 without writing code?
Yes. The Playground runs Suno v6 on your PopNow credits, needs no API key, and shows the matching code for every run.
All Suno models
Suno v6 is the dependable one for songs you already have in mind. v6 Wild takes more surprising, textured turns, and v6 Mini is the quick sketchpad, all at the same price per run.
