Sonilo V1.1 Music

• 🎵 Text-to-music generation with precise style, mood, instrumentation control.
• 📏 Exact duration control over generated tracks.
• 🔒 Trained on licensed catalogs via Shutterstock partnership.
• 🎯 Cleared for commercial use with no extra licensing.
• 🆕 Per-segment prompting and structure labels new in v1.1.
• 👁️ Also supports video-conditioned soundtrack generation.
• 🏢 Enterprise, API-first workflow from San Francisco's Sonilo.

Sonilo

Sonilo is an audio-focused AI organization specializing in generative sound. Its work centers on turning text prompts into original audio content — spanning full musical compositions and discrete sound effects — positioning it within the fast-growing niche of…

Sonilo V1.1 Music is a text-to-music model from Sonilo, a San Francisco company positioning itself around professionally licensed training data. You describe style, mood, and instrumentation in a single prompt and set an exact runtime, and the model composes a piece structured for that length, cleared for commercial use. Beyond text prompts, the broader Sonilo API can analyze an input video and return a soundtrack timed to scene changes, pacing, and mood.

Compared with the earlier v1.0 model, Sonilo reports that v1.1 tightens alignment: it locks beats, builds, and transitions to a video's pacing more precisely, following cuts and energy shifts across the timeline. V1.1 also adds per-segment control that v1.0 lacked — you can slice the timeline, assign a separate prompt to each section, and shape structure with labels like intro, verse, chorus, and bridge.

Licensing remains a defining feature. Sonilo states that, through partnerships including its Shutterstock agreement, v1.1 is trained on consented, compensated content, and every generation runs through content-ID and moderation checks before delivery.

Its companion release, Sonilo V1.1 Sound Effects, extends the same approach to contextual audio, letting production teams generate music and effects within a unified, video-native workflow.