Skip to main content

MiniMax Speech-02 HD API

MiniMax Speech-02 HD is a text-to-speech model by MiniMax, available on the Venice API as tts-minimax-speech-02-hd. Requests are anonymized, so the provider never sees your identity.Clone your voice from a short recording and generate natural speech in it across 30+ languages.

MiniMax Speech-02 HD API pricing

MiniMax Speech-02 HD specifications

How to use the MiniMax Speech-02 HD API

Send requests to POST https://api.venice.ai/api/v1/audio/speech with "model": "tts-minimax-speech-02-hd" and your API key.

MiniMax Speech-02 HD API FAQ

How much does the MiniMax Speech-02 HD API cost?

125per1Mcharactersofinputtext,about125 per 1M characters of input text, about 0.10 per minute of generated speech. Prices are in USD and can be paid in DIEM at parity.

What is the MiniMax Speech-02 HD model ID?

Use tts-minimax-speech-02-hd as the model parameter.

Is the MiniMax Speech-02 HD API private?

MiniMax Speech-02 HD is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

How many voices does MiniMax Speech-02 HD have?

15 voices, for example CalmWoman, CasualGuy, DeepVoiceMan. Output formats: mp3, pcm, flac.

Which endpoint does the MiniMax Speech-02 HD API use?

Call POST /audio/speech.

Related models