Sonilo

Features

• Video to sound effects. Generate sound effects that follow the on-screen action of an uploaded video, delivered as a standalone audio file or added back into a new video. Official source 1 ↗ · Official source 2 ↗ · Official source 3 ↗
• Text to sound effects. Describe a sound, such as glass shattering, and generate it from the prompt with a chosen duration. Official source 1 ↗ · Official source 2 ↗
• Video to music and text to music. Score a video with original music that follows its timing and mood, or generate music from a written description and a duration. Official source 1 ↗ · Official source 2 ↗
• Per-section direction. Give each section of a video its own music direction, or assign different sound effect prompts to different time ranges. Official source 1 ↗ · Official source 2 ↗
• Combined music and SFX mix. Generate a music bed and sound effects for one clip together and return a single mixed track or a new video; audio ducking mixes narration over background music. Official source 1 ↗
• Keeps existing audio. Sonilo works from the visuals only, so you can keep, adjust, replace or layer the video's original audio, and export the finished video or the music and effects as separate files. Official source 1 ↗
• Video translation and dubbing. Translate a video's speech and re-voice it in chosen languages, with optional lip sync, an editable translation, and support for uploaded .srt or .vtt subtitles. Official source 1 ↗
• Editor and game-engine plugins. Generate music and sound effects inside Premiere Pro, where Sonilo fills a marked timeline range, or inside Unity, Godot, Fab, Roblox Studio and Defold projects. Official source 1 ↗
• Developer API, SDKs, CLI and MCP. A REST API covers music, sound effects, ducking, dubbing and video analysis, with TypeScript and Python SDKs, a CLI, and a hosted MCP server for AI agents. Official source 1 ↗ · Official source 2 ↗

Pricing & free limits

Billing details

App credits are shared across all models and charged by output length: 18 credits per second for video-to-music and video-to-SFX, 5 for text-to-music and 4 for text-to-SFX, with a 15-second and 200-credit minimum per generation. Credits renew with the billing cycle; prices are in USD excluding taxes, and yearly billing saves 40%. Official source 1 ↗

API usage is metered per second and paid from a prepaid balance with optional auto top-up, separate from the app subscriptions; API output carries commercial-use rights without a Pro or Premium plan. Official source 1 ↗ · Official source 2 ↗

Free access & limits

The Free plan gives 2,000 credits every two weeks with preview-quality exports only, videos up to 3 minutes and 500 MB, one task at a time and personal, non-commercial use. The API offers 12 free trial calls, one or two per endpoint. Official source 1 ↗ · Official source 2 ↗

Best for & limitations

Adding licensed soundtracks and sound effects to ads, client videos and monetized YouTube or TikTok content without copyright risk. Official source 1 ↗

Generating music and sound effects for game scenes inside Unity, Godot, Roblox Studio and other engines. Official source 1 ↗

Building video-to-music and video-to-SFX generation into an app or production pipeline through the API. Official source 1 ↗

Localizing a video into other languages with dubbed speech and optional lip sync. Official source 1 ↗

• Free plan is non-commercial. Free output is for personal, non-commercial use and exports are preview quality; commercial rights start on Pro, and film, TV and broadcast need Premium. Official source 1 ↗
• Minimum charge per generation. Each app generation is billed for at least 15 seconds and 200 credits. Official source 1 ↗
• API limits and broadcast use. API videos over 6 minutes are rejected, the standard tier allows 60 requests per minute and 5 concurrent tasks, and film, TV, broadcast or streaming-service releases need sales approval first. Official source 1 ↗
• Watermarked output. Generated sound-effect audio carries an inaudible provenance watermark. Official source 1 ↗