Skip to main content

Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.Browse every model at this filtering level
minimax/speech-2.8-turbo/text-to-speech

MiniMax Speech 2.8 Turbo text-to-speech, optimized for speed and cost, reads a script in one of 472 system voices with a chosen emotion. It returns a 32 kHz mono MP3 by default, with speed, pitch, volume and sound tags like (sighs).

From $0.072/1,000 characters
Run model

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • 0:00 / –:––
    teasing-rival

    A teasing line in the Lively_Girl voice with emotion set to happy, on Turbo — MiniMax's faster, lower-cost variant with the same voices and controls as HD. The (laughs) cue at the start is performed, not read aloud.

    • happy
    • Lively_Girl
  • 0:00 / –:––
    last-round-bartender

    A bartender's tease in the Casual_Guy voice on Turbo. The (chuckle) cue before the punchline is performed, not read aloud.

    • Casual_Guy
  • 0:00 / –:––
    spanish-stay-a-little

    A Spanish line in the Sweet_Girl_2 voice with language forced to es, on Turbo. The (breath) cue is performed, not read aloud.

    • es
    • Sweet_Girl_2

This example starts at $0.072 per 1,000 characters. The Playground updates the estimate when you change the settings.