Qwen3.5 Omni Flash Realtime | EmpirioLabs AI Docs

Alibaba Cloud · Audio Generation

WEBSOCKET /v1/realtime

Speech in, speech out, over one socket, with separate text and audio token rates and per-turn billing.

At a glance

Field	Value
Model id	`qwen3-5-omni-flash-realtime`
Model release date	-
Input modalities	Audio, Text
Output modalities	Audio, Text
Context window	256K
Weight precision	-
Max output tokens	32,768
Region	Singapore
Features	realtime, speech_to_speech, audio_in, audio_out, multilingual
Native inference	No
New	Yes
Supported endpoints	`WEBSOCKET /v1/realtime`
Alternate model ids	`qwen3.5-omni-flash-realtime`, `alibaba/qwen3-5-omni-flash-realtime`

Pricing

Charge	Spec	Rate
Input	per 1M prompt tokens	per 1M prompt tokens $0.40; per 1M prompt tokens $3.00
Output	per 1M generated tokens	per 1M generated tokens $2.20; per 1M generated tokens $11.90

Example request

curl https://api.empiriolabs.ai/v1/audio/speech \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "qwen3-5-omni-flash-realtime", "input": "Hello from EmpirioLabs."}'

Parameters

Parameter	Type	Required	Default	Description
`voice`	enum	no	`"Tina"`	Speaking voice for the session. Set it with session.update before the model produces any audio. · Allowed: `Tina`, `Serena`, `Ethan`, `Dylan`, `Sunny`, `Peter`, `Kiki`, `Eric`
`instructions`	string	no	-	System guidance for how the model should behave and speak during the conversation.
`modalities`	string	no	`["text", "audio"]`	Which output types the model returns for a turn. Drop “audio” for a text-only reply.
`input_audio_format`	enum	no	`"pcm"`	Encoding of the audio you append to the input buffer: base64 16-bit PCM. · Allowed: `pcm`
`output_audio_format`	enum	no	`"pcm"`	Encoding of the audio the model streams back: base64 16-bit PCM. · Allowed: `pcm`
`turn_detection`	string	no	-	Server-side voice activity detection settings that decide when a turn ends and the model replies.

Notes

Full-duplex voice over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=qwen3-5-omni-flash-realtime, authenticated with the ordinary Authorization Bearer header. Configure the session with session.update over the socket: voice, instructions, modalities, and turn detection. This model’s voices differ from the earlier Omni generation, so set one it accepts or leave the default; an unknown voice ends the session rather than returning an error. Text and audio tokens are priced separately, and each completed turn is billed on its own from the usage the model reports.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/qwen3-5-omni-flash-realtime.