Describe a song. Get a full track. Skrrol runs ElevenLabs Music and Google Lyria 3 to compose soundtracks, podcast intros, and ad music from a sentence.
Text-to-music is the simplest music workflow: write a prompt, get a track. Skrrol AI runs ElevenLabs Music and Google Lyria 3 — both professional-grade music models — behind one panel. Pick the model, write the prompt, set duration, hit generate, and a full-length track lands in your library.
The prompt does the work. Cover genre ("lo-fi hip-hop"), instrumentation ("warm Rhodes, soft brushes, upright bass"), tempo ("around 75 BPM"), mood ("contemplative, late-night, hopeful"), structure ("intro for 8 bars, then a steady groove, no harmonic resolution at the end so it loops"), and reference style ("in the spirit of late-night jazz piano trio recordings, no vocals"). The more specific, the more reliable. For vocal tracks, include lyrics and singing style; for instrumental, say so explicitly.
The practical use cases are exactly what creators need: podcast intros and bumpers, video soundtracks, ad music beds, scoring for explainer videos, hold music, background loops for streams. With ElevenLabs Music's strong vocals and Google Lyria 3's broad instrumental range, the model lineup covers most creator and small-business briefs without compromise.
Tracks land directly on a stereo audio track in the Skrrol editor, ready for trimming, fading, ducking under voiceover, EQ, and beat-aligned cuts. If a take isn't right, refine the prompt and re-roll. For longer pieces, generate sections and stitch them on the timeline. Pricing sits between voice and video on the VL credits scale — a short bumper is cheap; a multi-minute full track uses more credits. Standard at €7.99 covers creator-scale music output.
ElevenLabs Music for polished song-like work; Google Lyria 3 for production-ready instrumental range. Pick per track or A/B both.
Be specific about genre, instruments, tempo, mood, and structure. Re-roll with refined prompts until the brief is hit.
Generate tracks at a specific run-time so they fit a video cut, podcast intro, or ad slot exactly.
Include vocals with prompted lyrics, or specify instrumental-only output.
Tracks land on a stereo audio track in the editor — apply ducking, fades, beat-aligned cuts, and EQ.
Outputs are usable for commercial creator and small-business work on paid Skrrol plans, subject to each model's licence.
Result: A seamless background loop suitable for streams, study videos, and YouTube backgrounds.
Result: A swelling instrumental cue for a montage, documentary intro, or trailer beat.
Result: A full pop song with verse, chorus, and bridge — useful for music videos, ads, and content backed by original songs.
Result: A 15-second bumper that sits well under a host's voiceover and ends on a natural beat.
Sign in, click Generate, pick the Music tab, and select Text-to-Music.
ElevenLabs Music for song-like output with strong vocals; Google Lyria 3 for production-ready instrumental range. Try both per prompt.
Cover genre, instrumentation, tempo, mood, and structure. Specify duration and whether you want vocals or instrumental.
Hit Generate. The track appears in your library when ready, with the prompt saved alongside.
Open the editor, drag the track onto a stereo audio track, align with video, apply ducking and fades.
Render the full project to MP4, or export the track alone as MP3 / WAV.
Skrrol AI uses VL credits across all generators — image, video, voice, and music. The same credit pool applies; heavier modalities (video) use more credits per generation than lighter ones (image, voice). Choose a plan and use credits across any generator.
Starter credits to experiment with prompt-driven instrumentals and short loops. Watermarked outputs.
8000 VL credits — soundtracks for weekly videos, short-form background music, podcast bumpers.
17000 VL credits — full-length tracks, multi-section arrangements, and per-scene music variants.
35000 VL credits — composer-level volume for ad campaigns, game scoring, and album-length output.
Each model has its own duration cap, typically up to a few minutes. For longer pieces, generate sections and stitch them on the timeline.
Yes — both models support vocal generation. Specify lyrics and singing style. For instrumental-only, say so explicitly.
Outputs are usable for commercial creator and small-business work on paid plans, subject to each model's licence.
Music sits between voice and video on the VL credits scale. A short bumper is cheap; a full multi-minute song uses more credits. Standard at €7.99 covers creator-scale music output.
Yes — every prompt is saved with its candidates. Refine and re-roll until the brief is hit.
Yes. Trim, fade, EQ, duck under voice, and align beats to video cuts in the editor's audio mixer.
Every generation opens directly in the Skrrol editor. These features are particularly useful as the next step after a text-to-music ai run.
Skrrol AI runs every generator next to a full pro editor. Your work stays on your device. Start free.