Voice Changer API
Transform uploaded audio into another voice through one async speech-to-speech task.
What is Voice Changer API?
Submit source audio, choose a target voice id, and retrieve the transformed result from the common task endpoint. Built for speech-to-speech workflows rather than immediate synchronous conversion.
Supported Models
Target voice workflow
Choose a voice id and process the file through one async task
Speech-to-speech model
Configure the route with a compatible voice transformation model
Voice settings
Tune similarity, stability, style, and noise cleanup when needed
Quick Start
curl -X POST "https://api.cheapaiapi.com/v1/task/voice-changer" \
-H "Authorization: Bearer sk_your_api_key" \
-F 'file=@audio.mp3' \
-F 'voice_id=21m00Tcm4TlvDq8ikWAM' \
-F 'model_id=eleven_multilingual_sts_v2' \
-F 'remove_background_noise=true'Why CheapAI?
Target Voice ID
Drive the conversion by selecting the exact target voice you want to apply.
Async Tasks
Create the conversion job once, then poll or receive the finished audio later.
Voice Controls
Use optional speech-to-speech tuning settings when your workflow needs more precision.
Async
Flow
Multipart
Input
/v1/task/:id
Polling
Audio URL
Output
Frequently Asked Questions
How do I retrieve the finished audio?expand_more
Poll the common task endpoint and read the returned audio URL when the task status becomes done.
Does it preserve the original speech content?expand_more
Yes, the workflow is designed to transform the voice while keeping the original spoken content.
Can I use a cloned voice as the target?expand_more
Use the voice inventory available to your workflow and route selection, including compatible custom voice ids where supported.
Start Building Today
Get $2 in free credits. Create an API key, set spend controls if needed, and start testing the current task-based endpoints.
Get API Key arrow_forward