Poe API
Qwen3.5-Omni-Flash
Qwen3.5-Omni Flash is the cost-efficient variant of Qwen's latest omni-modal model, supporting text, image, audio, and video understanding and interaction. It handles up to 3 hours of audio and 1 hour of video input, with audio input in 90+ languages and speech output in 30+ languages across 55 voice timbres.
Notes:
- Context Window: 256K
- Recommended: instruct the model to avoid markdown formatting in Text + Audio mode
Input limits:
- Images: up to 2,048 files, ≤20 MB each, min 10×10 px, aspect ratio ≤200:1
- Audio: up to 2,048 files, ≤2 GB each, up to 3 hrs
- Video: up to 512 files, ≤2 GB each, up to 1 hr
- Formats — Image: JPG, JPEG, JPE, PNG, WebP, BMP, TIF, TIFF, HEIC, GIF | Audio: AMR, WAV, 3GP, 3GPP, AAC, MP3 | Video: MP4, AVI, MKV, MOV, FLV, WMV
- Audio Input: 92 languages, 21 dialects
Output:
- Modalities: text only, or text + audio (audio-only not available)
- 55 voice timbres (default: Tina)
- Audio output: 29 languages, 7 dialects
This bot supports optional parameters for additional customization.
Powered by a server managed by @empiriolabsai. Learn more
- OFFICIAL
Build with Qwen3.5-Omni-Flash using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from EmpirioLabs AI
New
Seed-2.0-Code
New
Seedream-5.0-Lite-EL
New
Qwen3.6-Max-Preview
Gemini-3.1-Flash-TTS
Seedance-2.0-Fast-EL
Seedance-2.0-Pro-EL
DeepSeek-V3.2-EL
Wan-2.7
Qwen3.6-Plus
Wan2.7-Image