AI Voice Assistant with Advanced Generation Capabilities
Current Language: Not set
Current Model: Not set
Current TTS: Not set
20
Start Listening
Stop Listening
βοΈ
×
Settings
API Key:
Language:
English πΊπΈ
Russian π·πΊ
Model:
Text Generation Models
Gemma 2B IT π€
Mixtral 8x7B πͺοΈ
SmolLM 1.7B π£
Mistral Nemo π£οΈ
Yi 1.5 34B π§
Nous Hermes 2 Mixtral π¦
StableLM Zephyr 1.6B π
Phi-3 Mini 4K π§
DialoGPT Medium π¬
Gemma 1.1 7B IT π§
Gemma 2 27B IT π§
Meta-Llama 3 8B Instruct π¦
CodeLlama 34B Instruct π»
Image Generation Models
Stable Diffusion π¨
Dreamlike Photoreal π·
Soviet Diffusion XL π¨
FLUX.1 Dev πΌοΈ
OpenDalle V1.1 π
FLUX.1 Schnell π
Music Generation Models
MusicGen π΅
Text-to-Speech:
Standard π
kan-bayashi ποΈ
mms-tts-eng π£οΈ
VITS ENG US LJS π€
System Prompt (optional):
Enable Auto-Translation (for image and music generation)
Enable Chat Logging
Save
Reset to Default