StepFunText-to-speech

stepaudio-2.5-tts

JSON

StepAudio 2.5 TTS TTS GA streaming, http, websocket

Contextual TTS with global and inline natural-language delivery control plus zero-shot voice cloning from ~3 s of audio.

01 Price

$85.00per 1M chars

Cheaper than 6% of 95 priced text-to-speech models.

Text-to-speech $ per 1M characters, log scale 95 priced, 193 without a USD price

Text-to-speech: 95 models with a published USD price per 1M characters, from $1 to $100 and beyond, shown on a log scale.

other models this modelAll models by price

Price effective 2026-11-17 12:00 UTC+8 per StepFun pricing notice (recorded 2026-11-16). $85.00 per 1M characters: one Chinese char = 1, two English letters = 1, two punctuation marks = 1. Voice cloning $1.50 per voice.

Pricing source, checked 2026-11-16

02 Languages 6

03 Features 3 of 8 listed

"Not listed" means the provider's data doesn't mention it, not that the model lacks it.

04 Voices 7 compatible, browse all

  • Elegant Gentle

    Elegant, gentle female voice; sincere and reassuring.

    female / language not listed
    customer service, voice over, education

    elegantgentle-female
  • Lively Girl

    Bright, lively English female voice.

    female / English
    audiobook, video dubbing, voice assistant

    lively-girl
  • Lively Breezy

    Light, breezy female voice; engaging and persuasive.

    female / language not listed
    emotional companionship, customer service, education

    livelybreezy-female
  • Magnetic-voiced Male

    Deep, magnetic English male voice.

    male / English
    audiobook, video dubbing

    magnetic-voiced-male
  • Soft-spoken Gentleman

    Calm, gentle English male voice.

    male / English
    emotional companionship, audiobook

    soft-spoken-gentleman
  • Vibrant Youth

    Warm, approachable young English male voice.

    male / English
    audiobook, video dubbing, voice assistant

    vibrant-youth

05 Get this record

curl https://voicedex.dev/v1/providers/stepfun/models/stepaudio-2.5-tts

Free, no key needed. Use model id stepaudio-2.5-tts with StepFun's own API. API reference.

Esc

↑↓ move↵ open