Audio and video input
Accepts audio files (wav, mp3, m4a, flac, ogg) and video files (mp4, mov, mkv, avi, webm). For video, the audio track is enhanced and put back into the same video.
CatalogLatency Async; depends on audio duration Async true Rate Limit Per API key Max Input Duration-dependent; longer files take longer
cn8/studio-speech-clearance
Send an audio file (wav, mp3, m4a, flac, ogg) or a video file (mp4, mov, mkv, avi, webm)
Learn more about Speech Clearance Audio & Voiceasync (job)Instant previewaudioprocessingstudio
Try it
Source type
Audio or video with noisy speech
Result
The result shows up here
Upload your audio or video on the left and hit Run.
Overview
Send an audio file (wav, mp3, m4a, flac, ogg) or a video file (mp4, mov, mkv, avi, webm) and get back a clean, enhanced version of the speech. A neural speech-restoration model removes hiss, hum, and background noise and brings the voice forward, with smooth, click-free, high-quality output. For audio input you get an enhanced audio file; for video input you get the same video back with the cleaned speech track in place — the picture is untouched. This is an async job: submit it, poll until it's ready, then download the result.
Key capabilities
Noise removal and speech enhancement
Removes hiss, hum, and background noise and brings the voice forward for clear, intelligible speech.
High-quality, click-free output
The enhanced audio is delivered at high quality with smooth, click-free results from start to finish.
Video soundtrack enhancement
For video input, only the audio is replaced — the video itself is left exactly as it was. Output is a single MP4.
When to use it
Podcast and interview cleanup
Remove hiss, hum, and ambient noise from voice recordings before publishing.
Voiceover and narration
Enhance dialogue or narration tracks for video production.
Video soundtrack speech enhancement
Clean the speech in a video without touching the picture.
Input & output
input
Audio URL (wav, mp3, m4a, flac, ogg) or video URL (mp4, mov, mkv, avi, webm)
JSON body
output
Enhanced speech audio file URL, or the original video with enhanced audio (async job result)
JSONmedia URL
Guides & tips
How it works
- Submit an audio or video URL. For video, the audio track is enhanced and put back into the same video — the picture is left untouched.
- A neural speech-restoration model removes hiss, hum, and background noise and brings the voice forward, with smooth, click-free, high-quality output.
- Because it processes the whole file, this is an async job — submit it, poll until it's ready, then download the result.
Supported formats
- Audio: wav, mp3, m4a, flac, ogg
- Video: mp4, mov, mkv, avi, webm
- For video, only the audio is enhanced; the picture is left as-is.
Specs
Schema
Request body
mediaUrlrequiredstringURL of source audio (wav, mp3, m4a, flac, ogg) or video (mp4, mov, mkv, avi, webm)
Pricing
Billed per second of source audio. Two-part tariff: 5 credits base fee per job + 2 credits/second, minimum 5 billed seconds. Failed jobs are not billed.
| Service | Unit | Price |
|---|---|---|
| Speech Clearance | second | 2 credits/second |
For video input, billing is based on the audio track duration.
FAQ
Related models
Audio Background Separation
Separate background music before applying speech clearance for the best results.
Dubbing
Clean the speech first, then use Dubbing for translation and voiceover.
Voice Clone + TTS
Clean the source audio before cloning or TTS for the best results.
Video Upscale
Enhance speech audio and upscale video for full restoration.