Try MiniMax H3 (Text-to-Video) (Image-to-Video) from MiniMax →
Models
Agents
WorkflowsStudioPricingBlogDocs
ExploreDiscover models by categoryBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Explore models/
WorkflowActive

wiro / audio-merge

audio-merge

bywiro

Combine up to 10 audio files into one track by concatenating or mixing them, add optional crossfades, and export to common audio formats.

Utility
Model ID
audio-merge
Provider
wiro
Updated
1785772705
audio-merge
11
Comments
Average rating : 4.5 (19 users)
Providerwiro
Modelaudio-merge
Utility
wiro playground—wiro/audio-merge
Reset to defaults
Delete All
1 / 10
Maximum 10 audio allowed
utils-sampleinput-audio-1.mp3
URL

Required. At least two audio files. They are joined in the order they are added here.

Required. Default one after another. Playing one after another makes a single long track, so the result is as long as all the files together. Playing them at the same time layers them, for example a voice over music, and the result is as long as the longest file.

Optional. Default 0. Blends the end of each file into the start of the next one instead of cutting straight over, up to 10 seconds. Must be shorter than the shortest file. Used only when playing one after another.

Sample outputs
wiro-audio-merge-sample-1.mp3
Updated 1785772705
## Overview Audio Merge is a Wiro-native audio utility model for combining multiple audio clips into one output file. You upload at least 2 clips and choose a merge style: play them in sequence or layer them together. Sequence mode makes a single longer track, while mix mode overlays tracks for voiceover-plus-music style audio. It returns one merged audio file, which saves you manual editing and export steps. ## What you can build - Join an intro, main segment, and outro into one podcast-ready file - Merge many short voice notes into one continuous recording - Layer narration over background music for ads or reels - Combine multiple TTS segments into a single deliverable - Assemble a playlist-style “part 1 + part 2 + part 3” export ## Inputs - A set of at least 2 audio files, added in the exact order you want them processed (up to 10 total). - Audio provided as uploaded files or as direct URLs, as supported by the Wiro file workflow. - A merge style choice: - Play one after another (creates one longer file) - Play all at the same time (layers tracks into one mix) - An optional crossfade duration, from 0 to 10 seconds in 0.5 second steps. This only applies when you play clips one after another, and it must be shorter than the shortest clip. - An optional export format for the merged file: MP3, WAV, M4A, AAC, FLAC, OGG, or OPUS. If you don’t choose a format, the output keeps the first clip’s format. - An optional audio bitrate setting from 32 to 320 kbps for lossy formats (bitrate is ignored for WAV and FLAC). ## Outputs - One merged audio file in the selected format. - The merged file contains either a continuous sequence (end-to-end) or a single layered mix (overlaid tracks). - The result is returned as a downloadable audio asset, with file metadata such as content type and file size. ## Limitations - You can merge up to 10 audio files per run. - Crossfade only works in sequence mode, not in mix mode. - Crossfade must be shorter than the shortest input clip, or the run can fail. - In mix mode, the output duration matches the longest input clip. - Bitrate settings only affect lossy exports. WAV and FLAC ignore bitrate. - Mixing can create distorted audio if inputs are already very loud. - Low-quality or inconsistent inputs can cause problems. Examples include noisy recordings, clipped audio, and mismatched sample rates or channel layouts. ## Safety & compliance - Only merge audio you have rights to use and redistribute. - Get consent before mixing or publishing recordings of real people. - Don’t use this model to create or distribute deceptive audio meant to mislead others.

API quick start

Run audio-merge with a single API call.

POST https://api.wiro.ai/v1/Run/wiro/audio-merge
{
  "inputAudio": "https://your-cdn.com/input.mp3",
  "mode": "concat",
  "crossfade": 0,
  "outputFormat": "mp3"
}
View full API docs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
Getting StartedIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion