Follow a song idea from model choice to saved audio. This guide covers lyrics, timed sections, images, instrumental and language directions, result parts and generation limits.
Keep the idea and the audio connected
Use the workspace to organise prompts, lyrics and section timing, then follow generation and manage saved tracks. Lyria provides the model; ilovesong brings the creation steps together.
Lyria 3 Clip
Best for
Fast tests, hooks, loops, previews
Duration
Always 30 seconds
Output
MP3
Lyria 3.5
Best for
Fuller songs with verses, choruses, bridges
Duration
A couple of minutes, guided by your prompt
Output
MP3 or WAV (48 kHz stereo)
Sketch the sound with Clip. Once the direction works, develop the longer piece in Lyria 3.5.
Clip is fixed at 30 seconds, so it is ideal for testing genres, moods, and hooks.
For a song with space for verses, chorus and bridge, move the idea into Lyria 3.5.
Let a short Clip trial inform your next Lyria 3.5 request.
Give the model a musical brief it can interpret, rather than a mood word on its own.
Mention genre or genre blend: lo-fi hip hop, cinematic orchestral, indie pop, jazz fusion.
Name instruments: Rhodes, strings, brass, 808, acoustic guitar, vocal harmonies.
Set tempo and key when relevant: 85 BPM, D minor, G major.
Describe the mood and energy: nostalgic, aggressive, dreamy, uplifting, tense.
Include the intended running time in a Lyria 3.5 brief when length matters.
When the words are already written, give them their own space apart from arrangement notes.
Use section tags such as [Verse], [Chorus], [Bridge], [Intro], [Outro].
Keep your musical direction above the lyrics so the model sees both intent and words.
If you want no vocals, do not provide lyrics and explicitly say instrumental only.
Write a sequence of time windows and describe the musical event you want in each. These cues guide the pacing.
Example: [0:00 - 0:10] Intro, [0:10 - 0:30] Verse, [0:30 - 0:50] Chorus.
Use timestamps to control energy lifts, instrument entrances, vocal timing, and fade-outs.
This is especially useful for trailers, scene music, and directed builds.
Up to 10 pictures can accompany a Lyria request. Explain how their colours, story or atmosphere should translate into music.
Use moodboards, concept art, cover sketches, scene stills, or product visuals.
Only add images when visual direction really matters. Otherwise keep the request simpler.
Images work best when your prompt also explains what musical feeling the visuals should produce.
A backing track, trailer cue, game piece or beat may need instruments alone. State that requirement directly.
Use a phrase like: Instrumental only, no vocals.
This should appear directly in the prompt, not just as an implied preference.
A Clip can test the instrumental idea before you develop it with Lyria 3.5.
The language you write in helps guide Lyria's pronunciation and vocal approach.
If you want French lyrics, prompt in French.
If you want English vocals with Japanese section tags or notes, make that explicit.
Language control works better when you avoid mixing too many languages in one request.
A response has separate parts for written material and audio data, rather than a single uniform item.
Do not assume the first part is always lyrics or always audio.
Iterate through all returned parts and detect text versus inline audio data.
The text output can contain lyrics, structure notes, or other written material alongside the audio.
This tool is built on Google Lyria 3 and follows the same category of safety guardrails used across leading creative AI products. Avoid copyrighted lyrics, artist-name imitation, or requests to clone a recognizable performer. Focus on original briefs: genre, arrangement, instrumentation, emotion, language, lyrics, and structure.