AudioreAPI
Voice Cleaner API
Reduce noise from speech recordings and return clean voice tracks through one async task.
MP3 / WAV / AAC / OGG
Required
Any number from 0 to 1; default 1
source_file or voice_pack
Optional
mp3, wav, flac, aac, or ogg
Real-world workflows and production use cases you can build and ship with this model.

Use the voice changer API when your product already has a target voice pack id and needs to convert source vocals through an async backend call. The user chooses a pack, your backend sends voice_pack_id, and the task returns converted_mix output. That fits apps where voice selection happens in your own product before audio processing starts. The voice changer API keeps the audio task focused on conversion while your app owns pack browsing and permissions.
Change a voice
Set accent from 0 to 1 and choose source_file or voice_pack tonality. The voice changer API gives product teams clear controls without a complicated audio editor. That keeps the conversion form understandable for non-engineering users. Your UI can expose simple defaults first, then let advanced users tune only the fields they understand. The voice changer API works well when the product needs a guided voice-pack flow rather than a full editing surface.

Completed voice changer API tasks return the converted voice as a downloadable track. Store it, preview it, or send it into moderation and publishing flows. output.tracks can identify converted_mix when labels are available.
Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.
| Category | Unit | Price |
|---|---|---|
| Voice conversion | ||
| Source voice | 1 started minute | $0.2 200 credits |
The voice changer API requires voice_pack_id, so each task targets the configured voice asset your product selected. That keeps conversion behavior tied to a known pack. It also keeps pack selection outside the audio upload itself.
Accent uses a real 0 to 1 value, and tonality_reference accepts source_file or voice_pack. Those fields cover the common style choices without burying users in audio terms. Save the submitted values with each task so support and moderation teams can reproduce a result later.
Submit a task and poll /api/v1/tasks/:id until completion. The voice changer API fits the same async model as the other reAPI audio pages. Backend teams can reuse task storage, retries, and result handling. The voice changer API works best when the UI shows queued, processing, completed, and failed states clearly.
Generate a reAPI key from workspace settings. Keep the voice changer API call on your backend so voice pack ids and keys stay server-side.
OpenPOST model audio-voice-change with audio_url and voice_pack_id. Add accent, tonality_reference, dereverb_enabled, or encoder_format when your flow needs them.
OpenGET /api/v1/tasks/:id until completed. Download output.audio_urls or use output.tracks to find the converted_mix track.
OpenCommon questions about this model.
Explore more models in the same category.
AudioreAPI
Reduce noise from speech recordings and return clean voice tracks through one async task.
AudioreAPI
Extract the music bed from speech, clips, and mixed audio through an async API.
AudioreAPI
Remove vocals from a song URL and return labeled vocal and instrumental tracks.
AudioreAPI
Mureka V9 API on reAPI — lyrics in, finished song out, one async endpoint.
Try it in the playground or grab an API key to integrate now.