Does the AI handle sound effects?

Speech bubble text and bubble-contained sound effects are translated automatically. Art-integrated SFX drawn into illustrations are on our roadmap.

Can I edit the AI's output?

Yes. The built-in editor lets you click any bubble, edit the text, adjust font size and placement, and re-render the page instantly.

Como funciona a traducao de manga com IA

Q: How fast is the translation?

Most pages are ready in under a minute: the GPU pipeline takes a few seconds, then a quality check re-checks every bubble. Pages run in parallel, so a typical chapter is done in a few minutes.

Q: Is the free tier lower quality?

No. Every tier uses the exact same GPU pipeline, premium LLM engine, and neural inpainting. The only differences are page volume and editor/glossary access.

De paginas brutas a manga traduzido em segundos.

Passo 1

Envie suas paginas

Arraste e solte imagens PNG, JPG ou WebP -- ou envie um arquivo ZIP. Sem surpresas de tamanho: aceitamos ate 20 MB por pagina.

Upload individual pages or a full chapter as a ZIP archive. The translator accepts PNG, JPG, and WebP formats at any resolution. For best OCR results, use the original scan quality -- avoid heavily compressed JPGs. ZIP uploads process all pages in order, maintaining chapter continuity for the glossary.

Passo 2

OCR e deteccao de texto

Nosso detector com GPU (CTD) escaneia cada pagina e identifica baloes de texto, efeitos sonoros e caixas de narracao com precisao sub-pixel.

The Comic Text Detector (CTD) is a deep learning model trained specifically on manga, manhwa, and manhua layouts. It identifies speech bubbles, narration boxes, free-floating text, and sound effects -- including vertical Japanese text, open-background Korean text, and dense Chinese dialogue. Each detected region is passed to the OCR engine, which reads the source characters with support for Japanese, simplified Chinese, and traditional Chinese.

Passo 3

Traduzir e inpaint

Um modelo de linguagem grande traduz o texto do OCR para o idioma de destino. Enquanto isso, o LaMa Large faz inpainting (apaga) o texto original para que a pagina fique limpa.

Translation uses a premium LLM (currently Google Gemini 2.5 Flash) that receives all text regions on the page at once. This full-page context approach produces natural dialogue that respects speaker relationships, honorifics, and narrative flow. Simultaneously, LaMa Large neural inpainting removes the original text and reconstructs the underlying art -- even in detailed backgrounds and patterned screentone. If you have a per-series glossary, your locked terms are injected into the LLM prompt to ensure consistent names and terminology.

Passo 4

Diagramar e baixar

A traducao e renderizada na pagina com fontes combinadas e dimensionamento de baloes. Baixe suas paginas finalizadas individualmente ou como ZIP.

The typesetting engine places translated text onto the clean inpainted canvas with automatic font sizing to fit each bubble. The renderer uses a specialized manga-to-English engine that respects bubble boundaries and adjusts line breaks for readability. Download pages individually as PNG or get the full chapter as a ZIP. On Creator and Pro plans, you can review every bubble in the built-in editor before downloading -- adjusting wording, font size, and placement.

Performance and specs

Processing speed

Under a minute per page

The GPU pipeline translates and typesets a page in seconds, then a quality check re-checks every bubble, so most pages are ready in under a minute. Pages of a chapter are processed in parallel, so a typical 20-page chapter is usually done in a few minutes.

GPU infrastructure

NVIDIA A40 / RTX 4090

The pipeline runs on high-end NVIDIA GPUs (A40 or RTX 4090) for fast, consistent processing. GPU instances scale automatically to handle demand, so there is no queue during normal usage.

Supported formats

PNG, JPG, WebP, ZIP

Upload individual images in PNG, JPG, or WebP format (up to 20 MB per page), or a ZIP archive containing an entire chapter. Output is always PNG for maximum quality. ZIP uploads return a ZIP of all translated pages.

Idiomas suportados

Origem: Japones, Chines. Idiomas de destino abaixo.

Idioma	Codigo	Status
Ingles	ENG	Lancamento
Espanhol	ESP	Lancamento
Frances	FRA	Lancamento
Portugues (BR)	PTB	Lancamento
Alemao	DEU	Lancamento
Russo	RUS	Lancamento
Turco	TRK	Lancamento
Indonesio	IND	Lancamento
Vietnamita	VIN	Lancamento
Chines (Simplificado)	CHS	Lancamento
Chines (Tradicional)	CHT	Lancamento
Coreano	KOR	Lancamento
Arabe	ARA	Beta

Perguntas frequentes

Quao rapida e a traducao?

A maioria das páginas fica pronta em menos de um minuto: o pipeline de GPU (detecção, tradução, inpainting, diagramação) leva alguns segundos, e uma verificação de qualidade então reexamina cada balão em busca de texto transbordando, linhas ausentes e palavras não traduzidas. As páginas de um capítulo são executadas em paralelo, então um capítulo típico de 20 páginas geralmente é concluído em poucos minutos.

A IA lida com efeitos sonoros?

Texto de baloes de fala e traduzido e diagramado automaticamente. Efeitos sonoros integrados a arte (SFX desenhados na ilustracao) estao no nosso roadmap.

Posso editar o resultado da IA?

Sim. O editor integrado permite que voce clique em qualquer balao, edite o texto, ajuste tamanho e posicionamento da fonte, e re-renderize a pagina instantaneamente.

What source languages are supported?

Japanese and Chinese (both simplified and traditional) are supported at launch. Korean source text is on our roadmap. The pipeline handles vertical and horizontal text, tight bubbles, open backgrounds, and long-strip webtoon formats across all source languages.

Is the free tier lower quality?

No. Every tier, including the free pages, uses the exact same GPU pipeline, premium LLM engine and neural inpainting. The only differences between tiers are page volume, the watermark on pages translated without an account, the built-in editor and the per-series glossary.

Pronto para experimentar?

Envie suas primeiras paginas e veja os resultados em segundos.

Comece a traduzir