# Parish.ai

> Parish.ai is an all-in-one AI post production suite for filmmakers, video editors, marketers, podcasters, musicians, and content creators. It unifies best-in-class generative AI models for video, image, audio, music, and 3D into a single calm, professional, browser-based workspace with pay-as-you-go credits and no subscription.

Parish.ai combines models from Google (Veo 3.1, Imagen 4, Nano Banana 2, Nano Banana Pro), OpenAI (Sora 2, GPT Image 2), Black Forest Labs (FLUX.2 Max), ElevenLabs (TTS, SFX, Music), LALAL.AI (Andromeda stem separation, noise removal), Topaz Labs (video upscaling), LumaLabs (ray-flash-2 reframing, ray-2 modify), MMAudio (sound design), Trellis and Meshy v6 (3D), Tonn (audio mastering), and Fal.ai (face replacement, additional video models).

## Visual AI Tools

- [Generate Video](https://parish.ai/create-videos): Text-to-video and image-to-video generation with Veo 3.1 (default), Sora 2, Kling, Seedance, Hailuo, and RunwayML. Supports storyboard mode and synced audio.
- [Generate Image](https://parish.ai/gen-images): Text-to-image with Nano Banana 2 (default), GPT Image 2, FLUX.2 Max, Nano Banana Pro, and Imagen 4. Reference image input and AI prompt enhancement supported.
- [Upres Video](https://parish.ai/upres-videos): AI video upscaling and enhancement up to 4K via Topaz Labs (denoise, sharpen, frame interpolation).
- [Upres Image](https://parish.ai/upscale-images): AI image upscaling up to 4× with Real-ESRGAN, side-by-side comparison, and dynamic client-side resize for CUDA OOM handling.
- [Social Resizes](https://parish.ai/social-resizes): Generative video reframing to 7 social aspect ratios (9:16, 1:1, 4:5, 16:9, 21:9, etc.) using LumaLabs ray-flash-2.
- [Face Replacement](https://parish.ai/face-swap): Multi-face video face-swap with gender-aware matching, powered by Fal.ai.
- [3D Model](https://parish.ai/3d-asset): Image-to-3D with Trellis and text-to-3D with Meshy v6. Exports GLB, OBJ, FBX.

## Audio & Music AI Tools

- [Voice-Over](https://parish.ai/voice-over): Realistic multilingual text-to-speech with curated ElevenLabs voice talent, voice preview, and studio-quality export.
- [Music Stems](https://parish.ai/music-stems): Separate vocals, drums, bass, and instrumentals from any track with LALAL.AI Andromeda.
- [Sound Effects](https://parish.ai/text-to-sound): Generate three unique sound effect variations from a text prompt using ElevenLabs SFX.
- [Clear Dialogue](https://parish.ai/clear-dialogue): Remove background noise, hum, and reverb from dialogue with LALAL.AI noise removal.
- [Sound Design](https://parish.ai/sound-design): Synthesize sound effects synced to your video with MMAudio.
- [Create Music](https://parish.ai/generate-music): Compose original royalty-friendly music from a text prompt with ElevenLabs Music.
- [Audio Mix](https://parish.ai/audio-mix): Batch mix and master audio (loudness, EQ, dynamics) for podcasts, music, and video via Tonn API.

## Pricing

- [Account](https://parish.ai/account): Pay-as-you-go credits via Stripe. No subscription required. Each tool has a fixed credit cost shown before generation. Auto top-up available with card on file.

## Legal

- [Privacy Policy](https://parish.ai/privacy)
- [Terms of Service](https://parish.ai/terms)

## Optional

- [Sign In](https://parish.ai/auth): Email + password or Google OAuth.
- [Sitemap](https://parish.ai/sitemap.xml)
- [Full LLM context](https://parish.ai/llms-full.txt)