Bulgarian Text to Speech: Free, In-Browser, Nothing Uploaded
Bulgarian gets one neural voice in this build, and it only runs on a GPU — everyone else gets the system voice. Paste Bulgarian text, press play, and the audio is generated on your own device — no account, no upload, no character limit. This page is the honest version: which engines really speak Bulgarian (Български), which ones silently do not, and what each one costs you.
Which engines actually speak Bulgarian
Quick TTS ships four TTS engines and lets you switch between them from one dropdown — but not all four cover every language, and the gaps are not the ones you would guess from the marketing.
| Engine | Bulgarian? | What that means |
|---|---|---|
| Web Speech API | Yes | Your operating system's built-in Bulgarian voices. No download, works on every device including iPhone and Android. |
| Piper (WebAssembly) | No | Quick TTS does not ship a Piper Bulgarian voice yet — upstream carries one, but it has not passed our intelligibility checks — so the option is hidden rather than offered and then failing. |
| Kokoro-82M (WebGPU) | No | English only. Hidden on every other language, because a voice you cannot select is not an option. |
| Supertonic HD (WebGPU) | Yes | 44.1kHz studio-grade Bulgarian, one of thirty-one mapped languages. WebGPU-only, ~380MB cached once. |
Only one of Quick TTS's three neural engines speaks Bulgarian, and it is worth being blunt about the other two:
- Piper ships zero Bulgarian voices. Quick TTS does not ship a Piper Bulgarian voice in this build — the upstream catalogue does carry one, but it has not been through our per-voice intelligibility checks yet — so the engine option is hidden here rather than shown and then failing to load.
- Kokoro-82M is English-only and is hidden everywhere else.
- Supertonic HD does speak Bulgarian, natively, at 44.1kHz, as one of the 31 languages this build maps.
That is the same one-engine position Korean and Japanese are in. The difference for Bulgarian
is what the browser itself already offers: Windows ships a classic Microsoft Ivan
voice, and Edge adds two Azure-neural "Online (Natural)" voices, Kalina Online
and Borislav Online, which sound considerably better than the classic tier and are
a genuinely competitive free option even before Supertonic loads.
The honest limits
Being precise about that, because it is the whole picture for Bulgarian: Supertonic is WebGPU-only with no WebAssembly fallback tier, and there is no Piper voice sitting underneath it the way there is for Spanish or Russian. On a desktop with a working GPU you get studio-grade 44.1kHz Bulgarian after a one-time ~380MB cached download. On a phone, or a desktop without WebGPU, you fall back to whatever system voice the OS and browser combination happens to ship.
That floor is uneven across platforms. Windows plus Edge is the strongest combination, because Edge's Azure-backed online voices are considerably better than the classic Windows Bulgarian voice. macOS, iOS, and Chrome's own remote voice roster are inconsistent about shipping a named Bulgarian voice at all, so some visitors on those platforms may need to add a language pack manually or fall back to the classic OS voice.
Bulgarian is written in Cyrillic with lexical stress that is not marked in normal spelling, the same way English stress is not marked. A neural model has to guess which syllable of an unfamiliar word carries the stress, and getting it wrong is the most common way Bulgarian text-to-speech output sounds subtly foreign even when every sound is technically correct.
Nothing you paste is uploaded
This is the part that separates in-browser TTS from the cloud tools that look identical in a browser tab. A cloud tool sends your Bulgarian text to a server, synthesizes it there, and sends audio back — the page is a remote control. Quick TTS ships the engine to you instead and runs it on your CPU or GPU, so your text is never received by anyone. The test is simple: once the page and its model have loaded, the neural engines keep working with your network disconnected.
That matters most for the documents people actually want read aloud — a contract, a medical letter, coursework, an unpublished draft. It also means there is no "we phonemize non-English text on our server" asterisk, which is not true of every tool advertising local synthesis.
Reading Bulgarian documents, not just pasted text
PDF, DOCX, EPUB, ODT, RTF, HTML, TXT and Markdown are all parsed in the browser, so a whole Bulgarian EPUB or a long PDF opens and plays without a byte leaving your machine. A scanned PDF — a photo of text with no text layer — is handled by running OCR locally in WebAssembly rather than uploading the scan, which is precisely the case where local processing is worth the most.
Speed, volume and voice can all be changed mid-read and the current passage replays under the new settings without starting over. Switching the engine itself stops playback, so you press play once to start the new one — there is no mid-read handover of the remaining text between engines.
Frequently asked questions
Is Bulgarian text-to-speech free?
Yes. Quick TTS reads Bulgarian with no account, no character limit and no watermark. Synthesis runs in your browser on your own device, so there is no per-character server cost to meter and nothing to gate behind a sign-up.
Is my Bulgarian text uploaded anywhere?
No. The speech engine ships to your browser and runs locally, so the text you paste is turned into audio on your machine and never sent to a server. That is an architectural property, not a promise in a privacy policy — there is no server in the loop once the page has loaded.
What is the best Bulgarian TTS voice in the browser?
Supertonic HD is the highest-quality Bulgarian voice available here — 44.1kHz, running on WebGPU. It is also the only neural Bulgarian option: Piper ships no Bulgarian voice and Kokoro is English-only, so the alternative is your operating system's built-in voice. To get Bulgarian voices rather than English ones, open the app at quick-tts.com/bg/ — the neural voice list follows the page language.
Does it work on a phone?
The Web Speech API engine works on every modern phone with no download, and it is the default so the first play click always works. The neural engines are more demanding: Supertonic HD needs WebGPU and is effectively a desktop feature.
Can I download the Bulgarian audio?
Yes, as WAV or MP3, generated on your device. Anything longer than about 20,000 characters is packaged as a ZIP of audio parts so memory stays bounded on long documents.
Try it in Bulgarian — open the Български app, not the English one
This is the one piece of setup worth knowing, because it is not obvious: the neural voice list follows the language of the page you are on. On the English homepage the Supertonic reads with the English language tag — so Bulgarian text pasted there will be pronounced as though it were English. Open the Български version instead and the engine picks up Bulgarian automatically.
The one exception is Supertonic's "Auto language" toggle, which switches generation to a language-agnostic mode that reads mixed-language text with the right pronunciation per language without tagging anything by hand. That works from any page — it is the right choice for a document that is part Bulgarian and part English.
For the architecture behind all of this, see how in-browser text-to-speech works; for a tool-by-tool comparison with the other local TTS sites, see the comparison page.