Text, audio and video

Audiobooks, subtitles and voiceovers.

Pandrator is an open-source app for turning text and recordings into audio, subtitles and narrated video. Run local models or connect a speech API, check each stage, and export the files you need.

Download for Windows Download for Linux

A real Pandrator audiobook project with voice setup and preparation stages — A project in the app. Text, voices, generation and output have their own views.

Three starting points

What would you like to make?

Choose a starting task. You can inspect the text and audio, change a voice, or repeat a stage before exporting.

Audiobooks

Import documents, clean and segment the text, generate reviewable speech, and export chaptered M4B or common audio formats.

Subtitles

Transcribe audio or video, correct and translate the result, edit timing and text, then export SRT or subtitle tracks.

Voiceovers

Create speech from subtitles, synchronize it with media, and choose original, mixed, or dubbing-only audio.

Step by step

Guides with screens from the actual app

Prepare a book, correct captions, assign several voices or add sounds. Each guide follows a task through to a usable result.

Browse tutorials

Listen and watch

Examples with the model and source text

Compare the same narration passage through selected models, and watch a video with a voiceover and captions.

Open the examples

A visible workflow

Preparation and generation are separate steps.

01
Prepare

Import text, documents, subtitles, audio, video, or a supported public media URL.
02
Review

Inspect extraction, transcription, correction, translation, timing, and speech plans before moving on.
03
Generate

Use a local speech service, a configured commercial API, or a custom compatible endpoint.
04
Compare and export

Regenerate segments, compare takes and RVC variants, then assemble the required media.

Local and connected

Use the processing path that fits the material.

Pandrator does not require a cloud account. It can also use commercial services where their quality, language coverage, or convenience is useful.

Local processing

Speech and transcription on your own machine
Local OpenAI-compatible LLM servers such as LM Studio
Files, jobs, voices, and generated artifacts under your selected data root
No Docker or WSL requirement for the packaged Windows workflow

Connected providers

OpenAI and Google Gemini speech services
Supported cloud LLM providers for correction and translation
Custom OpenAI- or Gemini-compatible speech endpoints
Optional bounded Jina research for uncertain terminology

External providers may receive source text, subtitles, audio, or voice samples and may charge for usage. Review their terms before enabling them.

Voices and languages

Ready-made voices, cloning, and conversion are distinct tools.

Use a pre-built voice when you do not need a reference recording. Use a cloning model for a supplied sample. RVC is a later speech-to-speech conversion step, not a TTS model.

Find a compatible starting point Open the capability matrix

Common inputs and outputs

Documents, SRT, common audio and video inputs; M4B and common audio formats; MP4-oriented dubbed output with selectable tracks.

Open the capability matrix