StepAudio Realtime

Overview

Best for: Expressive Chinese-language companion or character voice apps.

At a glance

Prices are stepaudio-2.5-realtime per 1M tokens (cache-hit input $0.30); audio tokens per second not published. Platform concurrency tiers (5 at V0) may not apply to realtime. Docs are Chinese-first.

Features

• server VAD
• streaming audio deltas
• voice cloning
• persona instructions
• paralinguistic output (laughs, sighs)

Pricing

Free tier: Not confirmed.

Source: platform.stepfun.ai

Setup

1. Create an account on the StepFun open platform and an API key.
2. Connect to /v1/realtime with ?model=stepaudio-2.5-realtime and Authorization: Bearer <key>.
3. Send session.update (instructions, voice, pcm16 formats, server_vad), stream audio, play response.audio.delta.

Endpoint

wss://api.stepfun.com/v1/realtime?model=stepaudio-2.5-realtime

Authentication

Authorization: Bearer <STEPFUN_API_KEY>

// npm i ws   (China platform host shown; check the console for the international host)
import WebSocket from "ws";

const ws = new WebSocket("wss://api.stepfun.com/v1/realtime?model=stepaudio-2.5-realtime", {
  headers: { Authorization: `Bearer ${process.env.STEPFUN_API_KEY}` },
});

ws.on("open", () => {
  ws.send(JSON.stringify({
    type: "session.update",
    session: {
      modalities: ["text", "audio"],
      instructions: "You are a warm, concise assistant.",
      voice: "linjiajiejie",
      input_audio_format: "pcm16",
      output_audio_format: "pcm16",
      turn_detection: { type: "server_vad", prefix_padding_ms: 500 },
    },
  }));
});

export function sendPcm(buf) {
  ws.send(JSON.stringify({ type: "input_audio_buffer.append", audio: buf.toString("base64") }));
}

ws.on("message", (raw) => {
  const ev = JSON.parse(raw.toString());
  if (ev.type === "response.audio.delta") play(Buffer.from(ev.delta, "base64"));
});
function play(pcm) {}

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Plus 14 warnings that apply to all voice-to-voice APIs. See category warnings.

Limits

• Account rate tiers on the open platform range from V0 (under $15 top-up: 5 concurrency, 100 RPM) to V4 ($1,500+: 130 concurrency, 2,600 RPM); not stated whether these apply to realtime
• Session and context limits not documented on the model page

Models and products

Docs and sources

Docs

• StepAudio 2.5 Realtime (zh)
• Realtime developer guide (zh)
• Pricing (en)

Sources used

• platform.stepfun.com/docs/zh/guides/models/stepaudio-2.5-realtime
• platform.stepfun.ai/docs/en/guides/pricing/details
• marktechpost.com/2026/05/24/stepfun-releases-stepaudio-2-5-realtime-an-end-to-e...