
nex-n2.6From image Q&A to video summaries, one model to integrateText, image, and video input · Streaming text outputView integration guide

From speech and image generation to video understanding and real-time conversation, bring your ideas to life with the MOSS API.
curl -X POST "https://api.mosi.cn/v1/audio/speech" \
-H "Authorization: Bearer $MOSS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moss-tts-1.5-flash",
"input": "Welcome to the MOSS API.[pause 0.8s]Now generating speech.",
"voice_id": "94aa4989-c7e9-5007-ae42-ab401823e6c9",
"response_format": "mp3",
"delivery_method": "url"
}'Turns text into natural speech with low-latency streaming.
Tells speakers apart; built for meeting and interview transcripts.
Fine-tuned text-to-image model with text rendering and layout control.
Understands continuous image frames and streams incremental text.
Real-time audio-visual conversation with full-duplex speech and natural interruption.
Text conversations, image and video understanding, with streaming text output.