happyhorse-1.0/text-to-video
HappyHorse 1.0 with native 1080p output, cinematic motion, and multi-shot consistency.
ACE-Step Audio Inpaint is an audio editing model that re-renders a defined slice of an existing track without disturbing the rest. Pass in a source audio URL, mark the start and end of the slice, and describe the replacement with style tags plus an optional lyric block. The model synthesizes a fresh segment in place and stitches it back into the surrounding mix.
Output format: Audio only / source up to 60 minutes / slice range 0–240 seconds / provider-defined sample rate.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| audio* | Yes (*) | string | — | HTTPS URL to MP3 / WAV / FLAC, up to 60 min | Source audio file to edit. |
| tags* | Yes (*) | string | — | Free text | Comma-separated genre, mood, and instrument tags steering the segment style. |
| start_time_relative_to | No | string | start | start, end | Reference point for start_time. |
| start_time | No | number | — | 0 – 240 | Start of the editable segment in seconds. |
| end_time_relative_to | No | string | start | start, end | Reference point for end_time. |
| end_time | No | number | 30 | 0 – 240 | End of the editable segment in seconds. |
| lyrics | No | string | — | Free text or [inst] / [instrumental] | Lyrics for the regenerated segment; blank lets the model write its own. |
| seed | No | integer | -1 | -1 – 2147483647 | Random seed for reproducibility; -1 randomizes. |
ACE-Step Audio Inpaint on RunComfy uses time-based billing tied to the duration of the output audio it produces.
| Billing unit | Rate |
|---|---|
| Per second of output audio | $0.0002 |
Estimated cost examples
| Output duration | Approx. cost |
|---|---|
| 30 s | ~$0.006 |
| 60 s | ~$0.012 |
| 180 s (3 min) | ~$0.036 |
HappyHorse 1.0 with native 1080p output, cinematic motion, and multi-shot consistency.
Transform static visuals into cinematic motion with Kling O1's precise scene control and lifelike generation.
Generate cinematic videos from text prompts with Seedance 1.0.
LTX 2 retake video modifie the video by the prompt.
Render fluid, stylized scenes with fast, frame-consistent output
Premium image-to-video with the highest visual fidelity and motion realism in the Kling V3.0 family.
ACE-Step Audio Inpaint is an audio editing model from acestep-ai that rewrites a chosen time range inside an existing track while preserving the surrounding audio. In an audio-to-audio workflow on RunComfy, you provide a source URL, mark start and end times, and supply style tags or new lyrics, and ACE-Step Audio Inpaint regenerates only that segment. It is built for repair, restyle, and targeted remix work without re-rendering the full song.
ACE-Step Audio Inpaint is best suited for tasks like fixing off-beat or noisy bars, rewriting a single verse or chorus, restyling a section's instrumentation, and replacing a lyric line on a finished track. It also works well for short voiceover or sound-effect repairs where the surrounding audio must stay intact. Because it is segment-based, it fits remix, mastering prep, and content-edit pipelines more than full-song generation.
Compared to full text-to-music models, ACE-Step Audio Inpaint focuses on time-range edits and seamless blending into the existing track instead of producing a song from scratch. Compared to manual stem separation plus regeneration, it bundles segment selection, resynthesis, and crossfading into a single audio-to-audio pass. This typically gives technical artists tighter control over what changes and what stays the same.
Music producers, sound designers, game audio teams, and ad creatives benefit from ACE-Step Audio Inpaint when they need to repair, rewrite, or restyle specific sections of an existing track. Developers can wrap it into editing tools that let users mark a range and submit new tags or lyrics through an audio-to-audio interface. Content teams can also use it for last-mile fixes on trailers, podcasts, or game cinematics.
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. The editable segment in ACE-Step Audio Inpaint is bounded by start_time and end_time in seconds, with each value in the 0–240 range and anchored to either the start or end of the track. 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 Inpaint in the RunComfy AI Playground Web UI by adjusting the audio URL, segment range, tags, lyrics, and seed until the audio-to-audio result matches your target. Once the configuration is stable, call the same ACE-Step Audio Inpaint model through the RunComfy API with identical parameters to automate edits 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 Inpaint generations consume usd / credits from your RunComfy balance, and based on available provider information the model is billed at $0.0002 per second of output audio. 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 Inpaint page on RunComfy.
RunComfy provides access to the ACE-Step Audio Inpaint model and the audio-to-audio workflow, but commercial usage rights for the edited 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 edited 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.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.