Voice

Voice Changer

Convert a recording into another voice, preset or cloned. ElevenLabs speech-to-speech shape. Billed per second of input audio.

Last reviewed 2026-08-25

Convert audio

POST /elevenlabs/v1/speech-to-speech/{voice_id} takes audio and returns the same speech in the target voice. /stream streams the result. output_format is a query parameter.

from elevenlabs.client import ElevenLabs

client = ElevenLabs(base_url="https://api.mserve.ai/elevenlabs", api_key="ms_live_your_key")

with open("me.wav", "rb") as f:
    audio = client.speech_to_speech.convert(voice_id="21m00Tcm4TlvDq8ikWAM", audio=f, model_id="eleven_english_sts_v2", output_format="mp3_44100_128")
with open("converted.mp3", "wb") as out:
    for chunk in audio:
        out.write(chunk)

Prop

Type

The target voice_id can be a preset voice or a cloned voice.

Pricing

Billed per second of input audio at the chatterbox-vc rate.

ModelModel idPriceUnit
Kokoro 82Mkokoro-82m$3.00 per 1M charactersInput characters
Chatterboxchatterbox$6.00 per 1M charactersInput characters
Chatterbox Voice Conversionchatterbox-vc$0.060 per minuteInput audio, billed per second

On this page

Share feedback