Alibaba (Qwen) / qwen3-tts-flash-realtime
Qwen3 TTS Flash Realtime stands out for Low-latency bidirectional streaming TTS and Preset multilingual voices for immediate playback. It is best suited to realtime assistants and customer-service voice.
Context
—
Not applicable
Text input
$0.104
/ 10K chars
Generated output
Included
Quality
#58
Elo 1153
Overview
Qwen3 TTS Flash Realtime stands out for Low-latency bidirectional streaming TTS and Preset multilingual voices for immediate playback. It is best suited to realtime assistants and customer-service voice.
Audio output
Can produce audio output, commonly used for speech or voice experiences.
Streaming
Supports streamed responses for chat, assistants, and interfaces that need visible incremental output.
Model maker
Alibaba (Qwen)
Called through SeaLink's unified account, balance, and OpenAI-compatible API.
Protocol
Audio API
Base URL: https://api.sealink.io/v1
Pricing
The final charge follows generated usage and the applicable selector, such as resolution, duration, input type, or provider unit.
API
model
qwen3-tts-flash-realtimebase_url
https://api.sealink.io/v1Auth
Bearer $SEALINK_API_KEY# Realtime models use WebSocket sessions, not REST speech/transcription calls.wscat -c "wss://api.sealink.io/ws/realtime?model=qwen3-tts-flash-realtime" \-H "Authorization: Bearer $SEALINK_API_KEY"
import asyncioimport websocketsasync def main():uri = "wss://api.sealink.io/ws/realtime?model=qwen3-tts-flash-realtime"async with websockets.connect(uri, additional_headers={"Authorization": "Bearer <your-sealink-key>"}) as ws:print(await ws.recv())asyncio.run(main())
import WebSocket from "ws";const ws = new WebSocket("wss://api.sealink.io/ws/realtime?model=qwen3-tts-flash-realtime", {headers: { Authorization: `Bearer ${process.env.SEALINK_API_KEY}` },});ws.on("message", data => console.log(data.toString()));