All models

MiniMax Speech 2.8 HD

minimax/speech-2.8-hd
MiniMax TTSSpeech SynthesisVoice CloningMultilingualHigh Quality

MiniMax Speech 2.8 HD focuses on studio-grade audio generation with emotion control, multilingual support (40+ languages), and voice cloning.

Quick start

# Inspect the price — a plain request returns the 402 challenge:
curl -i https://api.glianalabs.com/v1/infer \
  -H "content-type: application/json" \
  -d '{
    "model": "minimax/speech-2.8-hd",
    "text": <string>
  }'

# Pay + run in one step with the mppx CLI (create a wallet: npx mppx account create):
npx mppx https://api.glianalabs.com/v1/infer \
  -J '{"model": "minimax/speech-2.8-hd", "text": "<string>"}'

Examples

Parameters

Input
emotion string

Emotion control for synthesized speech

format string required

Output audio format

pitch integer required

Pitch adjustment (-12 to 12)

sample_rate enum

Audio sample rate

speed number required

Speech speed (0.5 to 2)

text string required

The text to convert to speech. Maximum 10,000 characters.

voice_id string required

The voice ID to use for synthesis

volume number required

Speech volume (0 to 10)

Output
audio: URL to the generated audio file