Balabolka

Balabolka is a free, feature-rich text-to-speech (TTS) desktop application for Windows that converts on-screen text into spoken audio using Microsoft Speech API (SAPI 4, SAPI 5) and Microsoft Speech Platform voices already installed on your system. First released in 2006 and actively maintained through 2026, Balabolka has accumulated over 5 million downloads and remains one of the most widely used free TTS tools for Windows, supporting Windows XP through Windows 11.

Unlike cloud-based TTS services, Balabolka processes all text locally on your machine, ensuring complete privacy for sensitive documents. The application reads aloud text from DOC, DOCX, PDF, EPUB, ODT, RTF, HTML, and plain TXT files directly, eliminating the need to copy-paste content. Users can save generated speech to WAV, MP3, OGG, WMA, and other audio formats, making it practical for creating audiobooks, study materials, or accessibility recordings.

Balabolka provides granular control over speech output: users can adjust pitch from -10 to +10, speaking rate from -10 to +10, and volume levels independently per voice. The built-in pronunciation dictionary lets users define custom word pronunciations using phonetic rules, which is especially valuable for technical jargon, foreign names, or domain-specific vocabulary. Bookmarks can be inserted to split long documents into separate audio files at logical chapter or section breaks.

The application includes a command-line utility (balcon.exe) for batch processing and automation, enabling integration with scripts and workflows. A portable version is also available, requiring no installation and running directly from a USB drive. Additional features include built-in spell checking, text search-and-replace with regex support, and the ability to read text directly from the Windows clipboard. Balabolka supports interface localization in over 30 languages, though TTS voice availability depends on what the user has installed on their operating system. With an installed size under 30 MB and minimal CPU usage during playback, it remains a lightweight solution compared to commercial TTS suites.