Models
All ChatQT models
From GPT and Claude to Sora, Nano Banana, and ElevenLabs — all in one Persian-first workspace. One shared credit balance, so you can pick the right model for each task.
Major providers
Browse each provider page or jump straight into the app to compare outputs side by side.
Guide
Models by capability
Each capability includes multiple models from different providers, so you can switch inside the app and test what works best for your exact project.
Chat and reasoning
Access ChatGPT, Claude, Gemini, Grok, Kimi, DeepSeek (V3.2 and V4), GLM 5.2, and QT models such as R1 and Llama 4 Maverick from one workspace. Chat in Persian, generate in any language, and keep your history saved.
Image generation
Use Nano Banana Pro and Nano Banana, GPT Image 2, FLUX.2 Pro, Imagen 4 and Ultra, Grok Image, Seedream, and SD Ultra for everything from rapid concepts to polished visual output.
Nano BananaGoogle's lighter image tier for faster iteration and lower cost.
Nano Banana ProGoogle's pro image tier with better quality, stronger text-on-image, and tighter scene control.
GPT Image 2OpenAI's flagship image model for multi-style generation, high detail, and solid text rendering.
FLUX.2 ProBlack Forest Labs for photorealism and precise editing at a professional level.
Imagen 4Google's flagship image model with strong quality, text rendering, and flexible styles.
Imagen 4 UltraThe highest-detail tier in the Imagen 4 family for harder final visual polish.
Grok ImagexAI's faster text-to-image path for quick creative iteration.
SD UltraStability AI with very strong detail and polished visual output.
Video generation
Create professional clips with Sora 2, Veo 3.1 and Veo 3.1 Fast, Gemini Omni Flash, Grok Video, Kling 3.0 Pro, Seedance 2.0, Happy Horse 1.1, Minimax, Wan 2.2, and Hunyuan Video, then compare the outputs side by side.
Sora 2OpenAI for cinematic short-form video with synced audio.
Veo 3.1Google for high visual quality and natural motion in polished promos.
Veo 3.1 FastGoogle's faster route for more iteration at lower cost.
GeGemini Omni FlashGoogle/FalAI per-second video with low latency and cost.
Grok VideoxAI for text-to-video and image-to-video with a distinct style profile.
KlKling 3.0 ProKuaishou Gen 3 for the strongest motion control and longer-form scenes.
KlKling 3.0 StandardKuaishou Gen 3 balanced quality and cost.
Kling 2.6 ProKuaishou proven quality from the previous generation.
MinimaxMinimax video with 720p routes plus Director and Live tools.
Wan 2.2Alibaba for high-visual-quality text-to-video generation.
WaWan 2.1 ProAlibaba for 1080p clips up to roughly six seconds.
Hunyuan VideoTencent's T2V route available through AI Model.
Text to speech
Create natural voice output with ElevenLabs (Multilingual v2, Turbo v2.5), OpenAI TTS 1 and TTS 1 HD, Speechify Simba, and Google TTS Studio.
ElevenLabsMultilingual v2, Turbo v2.5, and v1 voicesOpenAI TTSTTS 1 and TTS 1 HD
SpeechifySimba English, Multilingual, and TurboGeminiGoogle TTS Studio
Speech to text
Transcribe audio and video files with Whisper and QTstt for fast, accurate speech-to-text in Persian and dozens of other languages.
WhisperOpenAI transcription across 99 languages with strong accuracy.
QTsttChatQT's Persian-optimized speech-to-text route for everyday spoken language.
Noise remover
Clean recorded audio with ElevenLabs Voice Isolator to reduce room noise, fan hum, wind, traffic, and background music.
ElevenLabs Voice IsolatorSeparates the human voice from room noise, traffic, wind, and background music.Every model, one credit balance
Credit packages differ only in the amount of credit you load. Every user gets access to all available features and models. See package details and estimated usage rates on the pricing page.
View pricingFAQ