Cleanvoice AI

Cleanvoice AI offers advanced audio and video editing tools powered by artificial intelligence. Their suite of features, from removing unwanted mouth noises to automatic background sound removal, helps creators produce cleaner, more professional content with ease. The platform's API provides extensive customization options for content editors and developers, making it a versatile solution for podcasters, video creators, and audio producers.

Overview of Cleanvoice AI's Services

The company's flagship product, the Mouth Sound Remover, automatically removes common mouth noises such as lip smacks, saliva crackle, and mouth clicks. The tool supports multi-track functionality, ensuring that mouth noises are removed from all tracks while maintaining file synchronization.

Cleanvoice AI processes up to 30 minutes of audio per session and supports multiple file formats including MP3, WAV, FLAC, and M4A. The system works across multiple audio tracks and maintains file synchronization during processing, as noted in their technical specifications.

The platform offers several additional features including background noise removal, filler words removal, long pauses/deadair audio enhancement, mouth sounds removal, and breath removal. Users can get started without any technical expertise, as no podcast editing tutorials are required.

In addition to audio editing tools, Cleanvoice AI provides several free services including podcast name generation, podcast audits, question generation, and episode title creation. These tools are designed to help users improve their overall production workflow and content creation process.

Audio Editing Features

The audio editing capabilities of Cleanvoice AI go beyond basic removal of mouth noises. Their suite of tools automatically removes background noise, including honking vehicles, crying babies, barking dogs, and slamming doors, while maintaining synchronization between audio tracks.

For content creators looking to enhance their productions, the platform offers detailed control through its API. Users can configure numerous parameters for audio processing, including options to remove dead air, filler words, stutters, and mouth sounds, while preserving music sections throughout the editing process.

When it comes to transcription, the platform offers both basic and enhanced features. It provides error-free transcription in multiple formats while optionally generating detailed summaries and social content optimized for sharing. The system maintains comprehensive control over the editing process through its API, allowing for boolean settings to enable or disable specific features like background noise removal and transcription.

The company's API supports processing of both audio and video files, making it versatile for creators working across multiple media types. Through detailed configuration options, users can fine-tune the editing process to suit their specific needs, from adjusting LUFS settings for audio level calibration to exporting custom timestamps of edited sections.

API Functionality and Integration

The Cleanvoice AI API enables automated editing through multiple endpoints, primarily for file uploads and job management. For creating edits, developers use the POST https://api.cleanvoice.ai/v2/edits endpoint, which requires a JSON payload containing the files array and config object.

The audio processing system accepts both single-track and multi-track audio uploads. Single-track files typically contain separate audio files for different speakers, while multi-track files combine all speaker audio into one file. Video files require the video parameter to be set to true.

The API offers extensive configuration options for editing audio processes. Users can enable or disable various features such as background noise removal, filler word deletion, dead air cleaning, mouth sound suppression, and breath removal. Additional capabilities include LUFS normalization settings and the ability to preserve music sections during processing.

For transcription and content analysis, the API supports generating comprehensive summaries and social-ready content. The system can produce detailed episode descriptions and key learning points, though these features require transcription to be enabled. The API maintains full control over the editing process through boolean settings for exporting timestamps and merging tracks.

All uploaded files are stored for seven days before deletion, though users can request earlier removal via specific deletion commands. The system provides structured JSON responses for API interactions, containing details on processing status, audio statistics, and download URLs for edited files.

Usage and Limitations

Cleanvoice AI's audio editing platform processes up to 30 minutes of content per session, with no sign-up or payment requirements to start using the service. The system handles multiple file formats including MP3, WAV, FLAC, and M4A, and works across both single-track and multi-track audio files. Video support requires enabling the video parameter in API requests.

When working with audio files, the system maintains its effectiveness across 30+ languages, though full support varies by language. English, German, and Romanian receive full support, while French, Dutch, and other languages have partial support. The exact capabilities for languages outside the fully supported list are unspecified due to limited documentation.

The platform removes background noise from a wide range of environmental sources, including vehicles, babies, dogs, and doors, while maintaining file synchronization between tracks. Through its API, users can configure detailed processing options for background noise removal, filler word deletion, dead air cleaning, and other audio enhancements.

Cleanvoice AI maintains comprehensive controls over the editing process via API parameters, including music section preservation and LUFS normalization settings. After processing, all uploaded files are stored for seven days before deletion, though users can request earlier removal if needed. The system provides structured JSON responses for API interactions, containing details on processing status, audio statistics, and download URLs for edited files.

Technical Specifications and Requirements

The system supports multiple audio file formats including MP3, WAV, FLAC, and M4A, allowing for processing of various file types and sizes. It maintains compatibility across different audio formats while processing up to 30 minutes of content per session.

Cleanvoice AI's API offers extensive configuration options for audio processing, including detailed controls for background noise removal, filler word deletion, dead air cleaning, mouth sound suppression, and breath removal. The system preserves music sections during processing and maintains file synchronization across multiple audio tracks.

The platform maintains comprehensive controls over the editing process through boolean settings for various features. Options include music section preservation, LUFS normalization settings, and the ability to export custom timestamps of edited sections. Processing results are stored for seven days after completion, with the option to request earlier deletion.

To upload audio files, the system provides both public links and support for signed URLs. The API supports both single-track and multi-track audio uploads, with combined files maintaining proper track synchronization during processing. All uploaded files, including raw inputs and edited outputs, are deleted seven days after processing unless explicitly retained through request.