Speech in, speech out, over one socket. Interruptible mid-reply, with voice activity detection deciding when to answer.
StepFunAudio Generation256K contextReleased Aug 6, 2026InternationalProprietary EndpointNewSpeech in, speech out, over one socket. Interruptible mid-reply, with voice activity detection deciding when to answer.
Session is configured with session.update events over the socket rather than request parameters.
Also known as StepFun StepAudio 3 Realtime
stepaudio-3-realtime/v1/realtimestepaudio-3-realtime-previewstepfun/stepaudio-3-realtimeLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
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. 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())Request parameters supported by the StepAudio 3 Realtime API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| voice | enum | soft-spoken-gentleman | soft-spoken-gentleman, magnetic-voiced-male, vibrant-youth, l... | Session voice, set with session.update before the model produces audio. It cannot be changed once the model has spoken, and any other value is rejected. |
| instructions | string | - | - | System instructions for the session: persona, speaking style, and boundaries. |
| modalities | string | ["text","audio"] | - | Response modalities for the session. |
| volume_ratio | number | 1 | 0.1 to 2 | Loudness of the spoken reply, relative to the default. Accepted range is 0.1 to 2.0. |
| input_audio_format | enum | pcm16 | pcm16 | Encoding of the audio you send. 16-bit PCM. |
| output_audio_format | enum | pcm16 | pcm16 | Encoding of the audio the model returns. 16-bit PCM. |
| turn_detection | string | {"type":"server_vad"} | - | Server-side voice activity detection. Decides when you have stopped speaking and the model should reply. Without it the model listens but never answers, so leave it... |
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. Each completed turn is billed on its own from the usage the model reports. This model is in preview and its capabilities may change.
On EmpirioLabs, StepAudio 3 Realtime is billed pay as you go: Input $1.50 per 1M prompt tokens; Output $10.00 per 1M generated tokens; Implicit cache read $0.30 per 1M cached input tokens. The live rate card on this page always matches what the API charges.
StepAudio 3 Realtime supports a 256K-token context window with up to 131,072 output tokens per response.
StepAudio 3 Realtime is served through WEBSOCKET /v1/realtime on api.empiriolabs.ai with standard bearer-token authentication.
Open the EmpirioLabs playground and press Start session to try it in your browser. StepAudio 3 Realtime runs over a WebSocket rather than a request and response, so to build with it start from the realtime voice quickstart. Connect from your server with your EmpirioLabs API key and the model id stepaudio-3-realtime, then stream audio in both directions.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Check out our pricing or reach out if you want your own model deployed on our stack.
