Cleanvoice is an AI audio and video post-production service designed for podcasts, interviews, and voiceovers, ideal for creators, editors, and teams handling large volumes of recordings. After uploading recorded audio and video files, you can select the cleanup items to apply, letting the system handle filler words, stutters, overly long pauses, and various disruptive noises without needing to manually build a transcript first.
Cleanvoice is an AI audio and video post-production service designed for podcasts, interviews, and voiceovers, ideal for creators, editors, and teams handling large volumes of recordings. After uploading recorded audio and video files, you can select the cleanup items to apply, letting the system handle filler words, stutters, overly long pauses, and various disruptive noises without needing to manually build a transcript first.
Beyond noise reduction, it can also adjust vocal volume and tone, generate transcripts, summaries, and show notes, and simultaneously edit multi-speaker audio tracks. For further post-production, editing timelines or markers can be handed off to your preferred software; developers can use the API and official SDK to integrate pre-recorded file processing into existing services.
Features
Filler word and stutter removal: Automatically detect filler words, stutters, and hesitation sounds in recordings, reducing the effort of manual segment-by-segment cutting.
Long pause trimming: Identify and remove overly long silences or blank segments to organize the pacing of the program's speech.
Background noise reduction and echo processing: Handle recording interferences such as wind, environmental noise, hum, background noise, echoes, and reverberations.
Mouth and breathing noise cleanup: Remove mouth clicks and breathing sounds to reduce minor noises in vocal recordings.
Voice enhancement and mixing: Adjust tone and vocal volume balance, with audio enhancement processing to improve original recordings.
Multi-track synchronized editing: Synchronize and handle filler words and pauses across different speakers' audio tracks; official documentation states the SDK does not yet stably support multi-tracks, which can be processed via API.
Custom processing templates: Choose existing templates or select cleanup items yourself, and mute selected segments while preserving audio-video synchronization.
Transcripts and show notes: Automatically transcribe audio and video content to generate summaries and show notes, without needing transcripts as a starting point for editing.
Timeline and marker export: Export editing timelines, timestamps, or modification markers for further adjustment in tools like Audacity, Audition, and Reaper.
Batch audio and video processing: Upload multiple episodes simultaneously, supporting common audio and video formats such as WAV, MP3, M4A, FLAC, and MP4.
API and workflow integration: Provide Python, JavaScript SDKs, and REST APIs, and integrate with Make and n8n to automatically process recorded audio and video files.
Use cases
After finishing a multi-person interview recording, simultaneously clear filler words and long pauses from each audio track, then export the timeline for detailed refinement.
After finishing narration or audiobook recordings, clean up breaths, mouth sounds, and background noise, and adjust vocal volume.
When a team regularly processes multiple podcast episodes, use batch upload or the API to apply the same cleanup settings and generate transcripts and summaries.
Categories: ,AI Resources, Tool Resources
Pricing
Paid, with a free trial available; pay-as-you-go 5-hour credits starting at US$11, valid for 2 years, excluding VAT; monthly or annual subscription amounts could not be confirmed.