Suno Add Vocals API

Add vocals to uploaded music. Only works with uploaded audio, not Suno-generated clips.

·Features·FAQ

Documentation

Model Variant

Clip ID *

ID of audio clip (from uploaded audio)

Audio File

Audio file URL

0/1

Click or drag & dropMP3, WAV, FLAC, OGG · Max 100MB

Vocal Lyrics

Lyrics/description for the vocals

Prompt

Custom mode prompt

Start Time (seconds)

Start time in seconds for vocal overlay

End Time (seconds)

End time in seconds for vocal overlay

Make Instrumental

Generate instrumental version

Title

Title for the result

Output

Your generated audio will appear here

Features

What Suno Vocals API offers

Adds vocals on top of a clip from uploaded user audio, keyed by clip_id

Optional audio_url file upload path when your workflow uploads first

Vocal description or lyric text via gpt_description_prompt plus optional prompt field

Optional start_s and end_s window in seconds for where vocals apply

Optional make instrumental flag and title on the same request

Chirp mv selection from v4 through Fenix v5.5

Async Suno feed polling after submit

Listed as Suno Add Vocals at $0.06 per generation on Unifically

Use cases

Built for

Primary

Instrumental beds: lay a top line and lyric over a beat you uploaded

Content: sung hook over a royalty safe backing you control

Demos: quick vocal pass before booking a session singer

Narrative audio: sung lines over a scored section with time bounds

Experimentation: iterate lyrics while keeping the same underlying clip_id

Remix prep: try vocal layers before stem based edits

FAQ

About Suno Vocals API

It is the Unifically Suno endpoint that adds generated vocals to audio you already uploaded. You supply clip_id from that upload, lyric or direction text, and optional start and end times in seconds.

No. The integration is built for uploaded audio clips, not Suno generated clips. Upload your instrumental first, then reference its clip_id.

Suno Add Vocals is priced at $0.06 per generation in the pricing table.

They limit the region in seconds where vocal generation is applied when you set them on the request.