psyche-subtitle-toolkit

Extract, translate, and mux ASS, SRT, and WebVTT subtitles in MKV files. Built for Psyche but usable as a standalone CLI or Rust library.

No cloud required. No telemetry. Every translation provider is opt-in.

Features

• Extract ASS, SRT, and WebVTT subtitle tracks from MKV files via mkvmerge/mkvextract
• Translate subtitle dialogue through 7 pluggable providers
• Protect ASS override tags ({\pos(...)}, {\an7}, etc.) during translation
• Automatic chunking (200 lines per request) for LLM context limits
• Concurrent chunk translation with configurable parallelism
• Retry with exponential backoff on HTTP, provider, and malformed output errors
• Mux translated subtitles back into the MKV, replacing the original track
• Process single files or entire directories
• Translate standalone .ass, .srt, and .vtt files without MKV (via translate-ass subcommand)
• Resume interrupted translations with --resume

Supported Providers

The --parallel column shows recommended concurrency for each provider.

Installation

cargo install --path .

Or build from source:

cargo build --release

Requirements

• mkvmerge and mkvextract from MKVToolNix must be in your PATH.

CLI Usage

Inspect MKV tracks

psyche-subtitle-toolkit inspect episode.mkv

Output shows all tracks with a * marking the selected ASS subtitle track:

* track 2: type=subtitles codec=SubStationAlpha language=eng name=HIDIVE_English
  track 3: type=subtitles codec=SubStationAlpha language=jpn name=

Translate subtitles

# Ollama (default, local)
psyche-subtitle-toolkit translate --input episode.mkv --to pt-BR --model gemma4:31b-cloud

# OpenAI
psyche-subtitle-toolkit translate --provider openai --api-key sk-... --model gpt-4o-mini --input episode.mkv --to pt-BR

# DeepL (free tier)
psyche-subtitle-toolkit translate --provider deepl --api-key YOUR_KEY --input episode.mkv --to pt-BR

# Google Translate
psyche-subtitle-toolkit translate --provider google --api-key YOUR_KEY --input episode.mkv --to pt

# Gemini
psyche-subtitle-toolkit translate --provider gemini --api-key YOUR_KEY --model gemini-2.5-flash-lite --input episode.mkv --to pt-BR

# OpenRouter (free model)
psyche-subtitle-toolkit translate --provider openrouter --api-key YOUR_KEY --model meta-llama/llama-3.3-70b-instruct:free --input episode.mkv --to pt-BR

Translate standalone subtitle files

# ASS file
psyche-subtitle-toolkit translate-ass --input source.ass --output translated.ass --to pt-BR --provider deepl --api-key YOUR_KEY

# SRT file (auto-detected by extension or content)
psyche-subtitle-toolkit translate-ass --input source.srt --output translated.srt --to pt-BR --provider deepl --api-key YOUR_KEY

# WebVTT file (auto-detected by extension or WEBVTT header)
psyche-subtitle-toolkit translate-ass --input source.vtt --output translated.vtt --to pt-BR --provider deepl --api-key YOUR_KEY

Resume interrupted translations

If a batch run is interrupted (crash, network failure), restart with --resume to skip already-translated files:

# First run — interrupted at file 15/20
psyche-subtitle-toolkit translate --resume --provider ollama --input /media/anime/ --to pt-BR

# Restart — skips files 1-14, continues from 15
psyche-subtitle-toolkit translate --resume --provider ollama --input /media/anime/ --to pt-BR

Progress is saved to .psyche-subtitle-toolkit-progress.json in the input directory and auto-deleted when all files complete.

Full options

-i, --input <INPUT>          MKV file or directory containing MKV files
    --to <TO>                Target language code (e.g. pt-BR, en, ja)
    --provider <PROVIDER>    Translation backend [default: ollama]
    --track <TRACK>          Specific subtitle track ID to translate
    --model <MODEL>          Model name [default: llama3.1]
    --ollama-url <URL>       Ollama base URL [default: http://localhost:11434]
    --openai-url <URL>       OpenAI base URL [default: https://api.openai.com]
    --anthropic-url <URL>    Anthropic base URL [default: https://api.anthropic.com]
    --api-key <KEY>          API key (required for openai, openrouter, anthropic, deepl, google, gemini)
    --deepl-url <URL>        DeepL base URL [default: https://api-free.deepl.com]
    --keep-temp              Preserve extracted/translated ASS files
    --dry-run                Show what would be translated without modifying files
    --source-lang <LANG>     Source language code (e.g. en, ja)
    --resume                 Save progress and skip already-translated files on restart
    --parallel <N>           Max concurrent chunk translations [default: 1]

Library Usage

Add to your Cargo.toml:

[dependencies]
psyche-subtitle-toolkit = { path = "../psyche-subtitle-toolkit" }

Translate an MKV file

use std::sync::Arc;
use psyche_subtitle_toolkit::{translate_mkv, TranslateMkvOptions, OllamaTranslator, Translator};

# async fn example() -> psyche_subtitle_toolkit::Result<()> {
let translator: Arc<dyn Translator> = Arc::new(OllamaTranslator::new("gemma4:31b-cloud")?);
translate_mkv(
    TranslateMkvOptions {
        input: "/media/anime/episode.mkv".into(),
        target_language: "pt-BR".into(),
        track_id: None,
        keep_temp: false,
        dry_run: false,
        source_language: Some("en".into()),
        resume: false,
        max_concurrent: 3,
    },
    translator,
).await?;
# Ok(())
# }

Translate ASS content directly

use std::sync::Arc;
use psyche_subtitle_toolkit::{translate_ass, AssSubtitle, OllamaTranslator, Translator};

# async fn example() -> psyche_subtitle_toolkit::Result<()> {
let ass = AssSubtitle::parse(&std::fs::read_to_string("source.ass")?)?;
let translator: Arc<dyn Translator> = Arc::new(OllamaTranslator::new("llama3.1")?);
let translated = translate_ass(ass, "pt-BR", Some("en"), 1, translator).await?;
std::fs::write("translated.ass", translated.render())?;
# Ok(())
# }

Implement a custom provider

use async_trait::async_trait;
use psyche_subtitle_toolkit::{Translator, TranslationRequest, Result};

struct MyTranslator { /* ... */ }

#[async_trait]
impl Translator for MyTranslator {
    async fn translate(&self, request: TranslationRequest<'_>) -> Result<String> {
        // Your translation logic here.
        // request.source_text is numbered: "<1> hello\n<2> world"
        // Return translated text in the same format.
        todo!()
    }
}

How It Works

1. Inspect -- mkvmerge -J identifies tracks and selects the ASS, SRT, or VTT subtitle
2. Extract -- mkvextract tracks pulls the ASS file to a temp directory
3. Parse -- The ASS parser reads dialogue lines, preserving headers and styles
4. Strip tags -- ASS override tags ({\pos(...)}, {\an7}) are removed and stored
5. Chunk -- Cues are split into 200-line batches
6. Translate -- Each chunk is sent to the provider as <N> text numbered lines (concurrent if --parallel > 1)
7. Retry -- Failed chunks (HTTP errors, malformed output) are retried up to 3 times with exponential backoff
8. Apply -- Translated text is mapped back to cues by ID
9. Reinject tags -- Original override tags are prepended back
10. Mux -- mkvmerge replaces the original subtitle track in-place

Testing

cargo test           # 101 unit + 12 doc-tests
cargo clippy -- -D warnings

Provider tests use wiremock to mock HTTP endpoints -- no real API calls.

Release Notes

v0.2.0

• SRT support — parse, translate, and render SubRip subtitles
• WebVTT support — parse, translate, and render WebVTT subtitles
• Anthropic provider — Messages API (/v1/messages) with custom endpoint support
• Remove --source-lang — all providers auto-detect source language, making the flag redundant
• Format auto-detection — translate-ass CLI auto-detects ASS/SRT/VTT by extension or content
• MKV format priority — ASS > SRT > VTT when multiple subtitle tracks exist
• Refactored pipeline — translate_document() helper shared by ASS, SRT, and VTT pipelines

v0.1.0

Initial release:

• 7 translation providers (Ollama, OpenAI, OpenRouter, DeepL, Google, Gemini)
• --parallel N for concurrent chunk translation
• --resume for interrupted batch recovery
• --dry-run to preview without modifying files
• Retry with exponential backoff on HTTP and malformed output errors
• DeepL/Google batch mode (per-line array elements)
• 200 lines per chunk
• Progress output to stderr
• translate-ass subcommand for standalone subtitle files

License

MIT