StepAudio 3 Realtime vs StepAudio 2.5 Realtime

StepAudio 3 Realtime vs StepAudio 2.5 Realtime at a glance

StepAudio 3 Realtime and StepAudio 2.5 Realtime are both StepFun models in the Audio Generation category, available through the EmpirioLabs API.

Key differences

• StepAudio 3 Realtime is the newer release (Aug 6, 2026); StepAudio 2.5 Realtime was released on Jul 16, 2026.
• Both models have a context window of 256K tokens.

StepAudio 3 Realtime vs StepAudio 2.5 Realtime: specs

StepAudio 3 Realtime vs StepAudio 2.5 Realtime: API pricing

Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.

StepAudio 3 Realtime vs StepAudio 2.5 Realtime: API parameters

Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.

StepAudio 3 Realtime vs StepAudio 2.5 Realtime: limits and notes

StepAudio 3 Realtime

Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=stepaudio-3-realtime, authenticated with the ordinary Authorization Bearer header. Audio is pcm16 in and out. The model listens while it speaks, so it can be interrupted mid-reply, and server-side voice activity detection decides when to answer. Set voice with session.update before the first audio; it cannot be changed once the model has spoken, and only the seven listed voices are accepted. Conversation is Chinese and English only. A session is billed by its length, from when it opens until it closes, in whole seconds, with a partial second counted as a full second. This model is in preview and its capabilities may change.

StepAudio 2.5 Realtime

Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=stepaudio-2-5-realtime, authenticated with the ordinary Authorization Bearer header. Audio is pcm16 in and out. The model listens while it speaks, so it can be interrupted mid-reply, and server-side voice activity detection decides when to answer. Set voice with session.update before the first audio; it cannot be changed once the model has spoken, and only the seven listed voices are accepted. Conversation is Chinese and English only. Each completed turn is billed on its own from the usage the model reports.

How to call StepAudio 3 Realtime and StepAudio 2.5 Realtime

StepAudio 3 Realtime holds a live conversation over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=stepaudio-3-realtime, not over the HTTP endpoints. Connect with the model id stepaudio-3-realtime and send your EmpirioLabs API key as an Authorization: Bearer header on the handshake. Audio travels both ways as base64 16-bit PCM. A browser cannot set headers on a WebSocket, so open this connection from your server and relay audio to the browser over your own socket. Both models are called through the same endpoint. Set model to stepaudio-3-realtime or stepaudio-2-5-realtime. Get an API key from the EmpirioLabs dashboard.

import asyncio, json, os, websockets

async def main():
    async with websockets.connect(
        "wss://api.empiriolabs.ai/v1/realtime?model=stepaudio-3-realtime",
        additional_headers=[
            ("Authorization", f"Bearer {os.environ['EMPIRIOLABS_API_KEY']}"),
        ],
        max_size=None,
    ) as ws:
        print(json.loads(await ws.recv())["type"])  # session.created

        await ws.send(json.dumps({
            "type": "conversation.item.create",
            "item": {
                "type": "message",
                "role": "user",
                "content": [{"type": "input_text", "text": "Say hello."}],
            },
        }))
        await ws.send(json.dumps({"type": "response.create"}))

        async for raw in ws:
            event = json.loads(raw)
            if event["type"] == "response.audio.delta":
                ...  # base64 audio chunk, append to your playback buffer
            elif event["type"] == "response.done":
                break

asyncio.run(main())

StepAudio 3 Realtime vs StepAudio 2.5 Realtime: common questions

What is the difference between StepAudio 3 Realtime and StepAudio 2.5 Realtime?

StepAudio 3 Realtime is the newer release (Aug 6, 2026); StepAudio 2.5 Realtime was released on Jul 16, 2026. Both models have a context window of 256K tokens. The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.

Which is newer, StepAudio 3 Realtime or StepAudio 2.5 Realtime?

StepAudio 3 Realtime is the newer release (Aug 6, 2026); StepAudio 2.5 Realtime was released on Jul 16, 2026.

Which has the lower rate, StepAudio 3 Realtime or StepAudio 2.5 Realtime?

The two models are priced on different units or tiers, so compare the live rate cards on this page. They always match what the API charges.

Can I switch between StepAudio 3 Realtime and StepAudio 2.5 Realtime without rebuilding my integration?

Yes. Both models use WEBSOCKET /v1/realtime with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.

Can I try StepAudio 3 Realtime and StepAudio 2.5 Realtime in the browser before integrating?

Yes. Open each model in the EmpirioLabs playground and press Start session to try it in your browser.