Ace Step Audio Outpaint: Extend Tracks With Matching Style and Vocals on Models and API | RunComfy

Ace Step Audio Outpaint is an audio extension model from acestep-ai that generates new content before, after, or on both sides of an existing track. In an audio-to-audio workflow on RunComfy, you provide a source URL, choose how many seconds to extend in each direction, and supply style tags or optional lyrics, and Ace Step Audio Outpaint produces continuations that blend with the original. It is built for lengthening tracks without re-rendering the source.

Ace Step Audio Outpaint is best suited for adding intros and outros, lengthening background music for video and podcasts, building extended remixes, and producing adaptive game or media audio that needs to keep going past its original cut. It also works well for songwriting, where you want to extend an existing idea in a matching style. Because it is bidirectional, it covers both opening and closing extensions in one pass.

Compared to manual loop-and-stitch workflows, Ace Step Audio Outpaint generates style-matched bars and blends them into the source instead of relying on repeating segments. Compared to full text-to-music models, it preserves the existing track and only adds new content at the requested ends, which keeps the original arrangement intact. This typically gives technical artists tighter control over how a track grows in length.

Music producers, video editors, game audio teams, and ad creatives benefit from Ace Step Audio Outpaint when they need to extend an existing track to fit a longer scene, episode, or campaign. Developers can wrap it into editing tools that let users mark a track and request seconds of intro or outro through an audio-to-audio interface. Content teams can also use it for last-mile fixes when a backing track is just shy of the final cut length.

Source audio is typically supplied as a public HTTPS URL to MP3, WAV, or FLAC, and based on available provider information may be up to about 60 minutes long. Each extension direction in Ace Step Audio Outpaint accepts a duration in seconds within the 0–240 range, with extend_before_duration controlling the start side and extend_after_duration the end side. Other constraints such as sample rate and exact format support depend on provider settings, so check the RunComfy parameter panel for the live limits.

You can prototype Ace Step Audio Outpaint in the RunComfy AI Playground Web UI by adjusting the source URL, extension durations, tags, lyrics, and seed until the audio-to-audio result matches your target. Once the configuration is stable, call the same Ace Step Audio Outpaint model through the RunComfy API with identical parameters to automate extensions from your backend or content pipeline. This keeps creative iteration in the browser and production runs in code, without changing model behavior.

Ace Step Audio Outpaint generations consume usd / credits from your RunComfy balance, and based on available provider information the model is billed at $0.0002 per second of total output (original audio plus both extension durations). New users typically get a free trial usd amount to experiment, after which usage follows the Generation rules shown on the model page. For current rates and any mode-specific differences, refer to the Generation section of the Ace Step Audio Outpaint page on RunComfy.

RunComfy provides access to the Ace Step Audio Outpaint model and the audio-to-audio workflow, but commercial usage rights for the extended audio depend on the license from the original model author and provider (acestep-ai), as well as any rights you hold over the source track you upload. Before releasing extended audio in commercial products, ads, films, or games, review the official ACE-Step license and your source-audio rights. For platform-side questions you can reach out to hi@runcomfy.com.