MiniMax Voice Cloning

MiniMax Voice Cloning is the premium tier for voice replication, submit a 30-60 second reference recording and the model trains a custom voice profile you can then drive with any text input via the standard TTS pipeline. Quality is industry-leading; identity persistence across long-form output is the strongest in the catalog. Pair with Fish Audio Voice Cloning when you want a tier-down cheap variant for higher-volume use cases.

Constraints & limits

The gateway auto-clamps requests to the model's limits where possible.

Quick start

This sample hits the text-to-speech endpoint. Change base_url and your key, then run it.

from openai import OpenAI

client = OpenAI(
    api_key="tl-xxxxxxxxxxxxxxxxxxxxxxxx",
    base_url="https://api.thalam.ai/v1",
)

response = client.audio.speech.create(
    model="minimax/voice-cloning",
    input="Welcome to Thalam, your unified gateway to AI models.",
)

with open("out.mp3", "wb") as f:
    f.write(response.content)