ElevenLabs Voice Changer API

Convert the voice in an audio file to a target ElevenLabs voice using speech-to-speech technology

ElevenLabs TTS ElevenLabs Dialogue ElevenLabs Sound Effects ElevenLabs Audio Isolation ElevenLabs Speech-to-Text ElevenLabs Voice Changer

Audio File *

URL of the source audio file to convert

0/1

Click or drag & dropMP3, WAV, FLAC, OGG · Max 100MB

Target Voice *

Target ElevenLabs voice ID

Model

ElevenLabs speech-to-speech model ID

Output Format

Audio output format (e.g. mp3_44100_128)

Input Audio Format

Input audio format hint: pcm_s16le_16 or other

Remove Background Noise

Strip background noise from input audio before conversion

Seed

Random seed for reproducible generation (0-4294967295)

Voice Stability

Voice stability (0-1)

Similarity Boost

How closely to match the target voice (0-1)

Style

Style exaggeration (0-1)

Speed

Speech speed multiplier

Speaker Boost

Boost speaker clarity

Output

Your generated audio will appear here

Features

What ElevenLabs Voice Changer API offers

Upload source audio and select a target ElevenLabs voice

Speech-to-speech conversion preserving original speech content and timing

Optional background noise removal before conversion

Voice settings control: stability, similarity boost, style, and speed

Multiple output formats including MP3, Opus, WAV, and PCM

Async generation with polling, consistent with other ElevenLabs tools

Priced at $0.0968 per minute of processed audio

Use cases

Built for

Primary

Content localization: re-voice narration in a consistent brand voice

Podcast production: standardize guest audio to a polished voice

Voiceover replacement: swap placeholder reads with final talent voice

Accessibility: convert speech to a clearer, more intelligible voice

Creative projects: transform character voices for audio dramas

Demo reels: produce multiple voice styles from a single recording

FAQ

About ElevenLabs Voice Changer API

A required audio_url of the source file and a voice_id for the target ElevenLabs voice. Optionally set model_id, output_format, remove_background_noise, seed, and voice_settings for fine-tuning.

The default is eleven_multilingual_sts_v2. You can override this via the model_id parameter.

Usage is billed at $0.0968 per minute of audio processed.

Yes. Enable the remove_background_noise toggle to strip noise from the input before voice conversion.