MiniMax Speech

minimax-speechMiniMax's large voice roster spans dozens of distinct character voices, from calm narrators to playful and dramatic personas.

Per 1K characters

$0.1000

Uptime · 24h

—

No traffic yet

Details

Type: Text to speech
Input: text
Output: audio
Voices: English_expressive_narrator, English_radiant_girl, English_magnetic_voiced_man, English_CalmWoman, English_Upbeat_Woman, English_Trustworth_Man, English_Aussie_Bloke, English_Gentle-voiced_man, English_WiseScholar, English_Comedian, English_ManWithDeepVoice, English_SereneWoman
Max characters: 8,000

Supported parameters

inputvoiceresponse_format

Last 24 hours

Requests per hour; red = provider errors.

Avg latency: —
Avg first token: —
Throughput: —

Use it

curl https://api.ultragpt.pro/v1/audio/speech \
  -H "Authorization: Bearer $ULTRAGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "minimax-speech", "voice": "English_expressive_narrator", "input": "Hello from UltraGPT!" }' \
  --output hello.mp3