Fish Audio Voice Clone

Fish Audio Voice Clone is the cost-tier complement to MiniMax Voice Cloning, same submit-reference-audio workflow but at a fraction of the price ($0.10 vs $2.40). Quality is meaningfully lower than MiniMax's premium tier, so use Fish for high-volume use cases (call-centre voicebots, IVR, internal tooling) where identity persistence matters less than per-voice economics.

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="fish-audio/voice-clone",
    input="Welcome to Thalam, your unified gateway to AI models.",
)

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