HiAPI
mirelo-sfx-2.0 详情页 Hero 图:21:9 宽幅,左侧柔光留白,右侧半透明玻璃声波圆盘与陶瓷波纹雕塑,名字以蚀刻发光字呈现,奶油、冰蓝、珊瑚与薰衣草色渐变。

Mirelo AI

Mirelo SFX 2.0

mirelo-sfx-2.0

An audio output model for sound effect generation scenarios, suitable for producing and batch-iterating sound effect assets for content such as videos and games

mirelo-sfx-2.0

Try mirelo-sfx-2.0

Input

Output

Fill in the parameters and run — results show up here.

Pricing

mirelo-sfx-2.0 per second

Unit Price $0.0215

Overview

mirelo-sfx-2.0 is a sound effect generation model accessed through the unified HiAPI.ai interface. It takes a text prompt and outputs audio. Callers describe the sound source, material, action, distance, and environment in the prompt, and specify a duration of 1 to 30 seconds (5 seconds by default). It is suited to video, game, and interactive content developers who need to produce sound effect assets in bulk, as well as teams that want to integrate sound effect generation into automated production pipelines.

Key Highlights

  • Generate sound effects directly from text descriptions — describe the sound source, material, action, distance, and environment in a prompt to get the corresponding audio, with no need to record or sample assets.
  • Specify generation duration in seconds — a single generation supports 1 to 30 seconds, with a default of 5 seconds, so sound effects can match the actual length of a shot or interaction event.
  • Unified billing by output seconds — cost is directly tied to the duration of the generated audio, making the cost of short and long sound effects predictable.

Capabilities

Prompt-driven sound effect generation: describe the desired sound in up to 2000 characters of text, and the model outputs the corresponding audio, eliminating asset search and recording.

Controllable audio duration: use the duration parameter to specify an output length of 1 to 30 seconds, making it easy to align with the rhythm of video clips, animated shots, or interaction feedback.

Structured sound description: prompts support combinations of sound source, material, action, distance, and environment, making it easy to portray the spatial sense and texture of sound effects for specific scenes.

Unified interface access: called through a single HiAPI.ai interface, the output audio can be fed directly into existing audio or content pipelines.

Use Cases

  • Video editors adding ambient sound to shots — enter a sound description corresponding to the shot content and set the duration to get ambient sound effect assets that can be laid directly onto the timeline.
  • Game developers creating interaction sound effects — generate short sound effects based on action and material descriptions for event-triggered playback such as button feedback, collisions, or item pickup.
  • Content teams iterating on sound effect options in bulk — adjust the description wording in the same prompt and generate multiple times to quickly compare different options, then use the chosen one in the final cut.

Limitations and Selection Advice

Currently only text prompts are supported as input; reference audio cannot be uploaded for timbre transfer or style matching. The output duration limit is 30 seconds, and longer continuous sounds need to be generated in segments and stitched together manually. If the task requires human voice, music, or songs with lyrics, choose the corresponding speech synthesis or music generation model. For situations with strict requirements on details such as the spectrum and dynamics of sound effects, it is recommended to generate candidate assets first and then manually screen and post-process them.

  • New model New model: mirelo-sfx-2.0

Related Models

View all models →

Same Type