Introduction
The Suno v6 Mini API is for auditioning song ideas: our examples move from a 0:37 acoustic theme to a self-written 3:25 folk song and a 3:17 jazz instrumental, at one flat request price. Start Mini from a sentence with generate_lyrics enabled, or give it a lyric sheet to audition an idea already written; instrumental makes the draft wordless instead. For Mini, choose the mode before refining a sketch: title, persona and style controls require custom lyrics or instrumental; images, audio and video references require generated lyrics, otherwise the request errors.
| Field | Value |
|---|---|
| Input | Text |
| Output | Audio |
| Required field | Start a Mini idea with genre, mood and instruments: up to 1,000 characters with lyrics or instrumental, otherwise 3,000 for lyric generation. No surcharge for this Mini setting. |
| Optional fields | For Mini, choose the mode before refining a sketch: title, persona and style controls require custom lyrics or instrumental; images, audio and video references require generated lyrics, otherwise the request errors. |
| Result | A Mini idea becomes two complete MP3 takes, so the acoustic sketch can be judged as two arrangements rather than one preview; the request price includes both. |
| Lyrics | Start Mini from a sentence with |
| Billed quantity | A Mini idea becomes two complete MP3 takes, so the acoustic sketch can be judged as two arrangements rather than one preview; the request price includes both. |
| Retention | Save the Mini takes you want within the 14-day audio retention window, especially if the sketch will become a later production; responsibility for submitted lyrics and publication remains yours. |
Key features & highlights
Our theme song, unplugged
The SpicyAPI theme song as Mini plays it: strummed acoustic guitar, hand claps and a warm male voice. All 10 lines were sung in the order written and the section tags stayed silent; of the three versions of this song, Mini’s is the shortest.
A song written around one image
One sentence about a couple sharing a blanket on a hillside and watching fireflies, with no lyrics, became “The Little Lights”. Mini wrote every verse and the chorus, then sang them; at 3:25 it is the longest of our samples.
Calm instrumentals for the background
“Velvet Corner Table” is slow lounge jazz at 72 bpm with brushed drums, upright bass, muted trumpet and Rhodes piano, and no vocal. Use instrumental mode for music under a video, a menu screen or a stream.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | Yes | Start a Mini idea with genre, mood and instruments: up to 1,000 characters with lyrics or instrumental, otherwise 3,000 for lyric generation. No surcharge for this Mini setting. at least 1 characters · at most 3000 characters |
lyrics | No | Supply Mini with up to 5,000 characters to sing, placing section tags on separate lines; repeat chorus lines where you want them sung again. No surcharge for this Mini setting. at least 1 characters · at most 5000 characters |
generate_lyrics | No | Enabled initially: Mini writes words from prompt when neither lyrics nor instrumental is supplied; your submitted lyrics take precedence. No surcharge for this Mini setting. Default: |
instrumental | No | Enable for a Mini backing-track sketch without singing; defaults to false and uses prompt as a style brief of up to 1,000 characters. No surcharge for this Mini setting. Default: |
title | No | Label a Mini draft with an optional name of up to 80 characters; generated-lyrics mode names the song itself. Mini fine controls require your own lyrics or instrumental mode. at least 1 characters · at most 80 characters |
negative_prompt | No | Exclude unwanted elements from a Mini sketch with a short list, such as distortion or spoken delivery; optional, up to 500 characters. No surcharge for this Mini setting. at least 1 characters · at most 500 characters |
vocal_gender | No | Suggest female or male for the Mini lead; this is a preference with no measured success rate, not a guaranteed singer selection. |
style_weight | No | For Mini drafts, controls adherence to the style brief on a 0–1 scale, in 0.01 steps. Mini fine controls require your own lyrics or instrumental mode. |
weirdness | No | Set the experimental freedom of a Mini sketch from 0, conventional, to 1, adventurous, in steps of 0.01. Mini fine controls require your own lyrics or instrumental mode. |
audio_weight | No | For Mini vocal drafts, sets the influence of persona audio: 0–1, step 0.01; not supported for wordless music. Mini fine controls require your own lyrics or instrumental mode. |
variety | No | Mini can vary the style prompt with an integer 0–4, default 1; 0 preserves your style tags, according to Suno’s untested setting description. |
persona_id | No | Reuse an existing Suno persona in a Mini draft by sending its ID together with |
persona_model | No | For the Mini persona ID, choose |
image_urls | No | Give Mini up to 5 visual starting points in JPEG, PNG or WebP, at most 10 MB each. For Mini references, leave lyrics empty, instrumental off and |
reference_video_urls | No | Build a Mini song idea around one MP4 or WebM, no more than 100 MB or 241 seconds. For Mini references, leave lyrics empty, instrumental off and |
reference_audio_urls | No | Inspire Mini with one authorized MP3 or WAV reference, 6 seconds to 30 minutes and at most 500 MB. For Mini references, leave lyrics empty, instrumental off and |
Pricing
$0.072 / request
A Mini idea becomes two complete MP3 takes, so the acoustic sketch can be judged as two arrangements rather than one preview; the request price includes both.
Use cases
Quick drafts and sketchbooks
Turn a line, a title or a half-written verse into a full song to hear whether the idea has legs. Suno built v6 Mini to make that step easy.
Folk, acoustic and singer-songwriter ideas
Our sample, the SpicyAPI theme song as a sunny acoustic track, came back with a warm male voice over strummed guitar and hand claps, every line of the lyric sheet sung in order.
Lots of takes for a small project
Newsletters, podcast intros and classroom songs often need several tries. Two versions per request make each try count.
Calm instrumentals
Lounge jazz and soft background beds with no vocals, such as the 3:17 piece we generated for the instrumental sample.
Prompt guide & pro tips
Start from an idea
Mini’s acoustic example uses strummed guitar and hand claps: describe that sort of instrumentation, tempo and voice directly, with section tags on their own lyric lines.
Or bring a lyric sheet
Supply Mini with up to 5,000 characters to sing, placing section tags on separate lines; repeat chorus lines where you want them sung again. No surcharge for this Mini setting.
Listen to both
Start Mini from a sentence with
generate_lyricsenabled, or give it a lyric sheet to audition an idea already written; instrumental makes the draft wordless instead.
Song ideas in practice
The Suno v6 Mini API is for auditioning song ideas: our examples move from a 0:37 acoustic theme to a self-written 3:25 folk song and a 3:17 jazz instrumental, at one flat request price. Start Mini from a sentence with generate_lyrics enabled, or give it a lyric sheet to audition an idea already written; instrumental makes the draft wordless instead. For Mini, choose the mode before refining a sketch: title, persona and style controls require custom lyrics or instrumental; images, audio and video references require generated lyrics, otherwise the request errors.
Listen to this model
Our theme song, unplugged
The SpicyAPI theme song as Mini plays it: strummed acoustic guitar, hand claps and a warm male voice. All 10 lines were sung in the order written and the section tags stayed silent; of the three versions of this song, Mini’s is the shortest.
A song written around one image
One sentence about a couple sharing a blanket on a hillside and watching fireflies, with no lyrics, became “The Little Lights”. Mini wrote every verse and the chorus, then sang them; at 3:25 it is the longest of our samples.
Calm instrumentals for the background
“Velvet Corner Table” is slow lounge jazz at 72 bpm with brushed drums, upright bass, muted trumpet and Rhodes piano, and no vocal. Use instrumental mode for music under a video, a menu screen or a stream.
Choose what it should invent
Start Mini from a sentence with generate_lyrics enabled, or give it a lyric sheet to audition an idea already written; instrumental makes the draft wordless instead.
Mini’s acoustic example uses strummed guitar and hand claps: describe that sort of instrumentation, tempo and voice directly, with section tags on their own lyric lines.
Keep the settings compatible
For Mini, choose the mode before refining a sketch: title, persona and style controls require custom lyrics or instrumental; images, audio and video references require generated lyrics, otherwise the request errors.
Mini can vary the style prompt with an integer 0–4, default 1; 0 preserves your style tags, according to Suno’s untested setting description. Mini fine controls require your own lyrics or instrumental mode. No surcharge for this Mini setting.
Compare and save the takes
A Mini idea becomes two complete MP3 takes, so the acoustic sketch can be judged as two arrangements rather than one preview; the request price includes both.
Mini offers no working duration selector here; the 3:25 folk sample and 3:17 jazz sample illustrate lengths shaped by the material, not a timed commission.
Save the Mini takes you want within the 14-day audio retention window, especially if the sketch will become a later production; responsibility for submitted lyrics and publication remains yours.
Content review
Mini is a filtered music model, not an unrestricted NSFW option: Suno rejected stronger lyrics and descriptions in SpicyAPI tests, without charge; platform access cannot remove that filter. SpicyAPI adds no separate filter to Mini. For unrestricted music generation, see the Seed Audio 1.0 family.
Mini tests rejected prompts naming real artists; specify the acoustic texture, instruments and singing character you want without an artist attribution.
Mini is a filtered music model, not an unrestricted NSFW option: Suno rejected stronger lyrics and descriptions in SpicyAPI tests, without charge; platform access cannot remove that filter. SpicyAPI adds no separate filter to Mini. For unrestricted music generation, see the Seed Audio 1.0 family.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "suno/v6-mini/text-to-audio",
"input": {
"prompt": "Calm ambient pads with a slow rising motif"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.


