Text to Speech (TTS, Free)
Paste your text, pick a natural AI voice and save it as WAV or MP3 — or use your device voices instantly.
Before you start Copyright, AI-voice disclosure and the 400 MB download (tap to read)
- The copyright in a text belongs to its author. If you plan to publish someone else's writing, check that you have permission.
- The "High-quality AI voice" runs Supertone's Supertonic 3 model directly in this browser. Your text and audio stay on this device, but if you publish the result, disclose that it is AI-generated.
- Don't use the AI voice to impersonate someone, create deepfakes, do anything illegal, harass anyone, or spread disinformation. See the OpenRAIL-M license for details.
- The AI voice downloads about 400MB of model files the first time you use it (Wi-Fi recommended). On the "Device voices" tab, voices marked "online" may send your text to the browser or OS provider's servers.
Loading the tool...
Hearing text read aloud helps with proofreading, presentation practice and accessibility. This tool offers two modes. The "High-quality AI voice" runs Supertone's open-source Supertonic 3 model directly in this browser, producing natural, human-like narration that you can save as a WAV or MP3 file. The "Device voices" tab uses the speech synthesis built into your browser, so you can use it right away without installing anything or downloading a model.
What is the High-quality AI voice (Supertonic 3)?
Supertonic 3 is an on-device text-to-speech model that supports 31 languages, including Korean, English and Japanese. It runs inference with ONNX Runtime Web entirely inside this browser, so your text never leaves your device. Choose from 5 male and 5 female voices, a speed from 0.8x to 1.5x, and a quality setting of 4, 8 or 16 denoising steps — higher steps sound more natural but take a little longer. You can paste up to 5,000 characters at once; within that limit, longer passages are split into paragraph-sized chunks automatically, generated in order and stitched into a single audio file. The model files (about 400MB) download only the first time; after that they're cached in this browser. If your device supports WebGPU, it's used automatically for much faster generation, with an automatic fallback to WebAssembly (WASM) otherwise.
When to use it
- Proofread a draft or practice a talk by listening to it
- Listen to a document when reading on screen is hard
- Get a rough idea of how text in another language sounds
- Quickly make a temporary voice-over for a video
- Try different speeds and pitches for a different feel
How to use (High-quality AI voice)
- Open the "High-quality AI voice" tab and pick a language (Korean, English, Japanese or others) and a voice (Male 1-5, Female 1-5).
- Choose a speed (0.8 to 1.5x) and quality (4, 8 or 16 steps), then paste your text (up to 5,000 characters).
- Press "Pre-download" to fetch the model ahead of time, or just press "Generate AI voice" to start right away. The model (about 400MB) downloads only once.
- The result plays automatically; save it as a WAV or MP3 file.
How it works
The high-quality voice is Supertone's Supertonic 3 model running with ONNX Runtime in your browser; its model files (about 400 MB) are downloaded once from our model storage (models.dagotools.com, with Hugging Face as a fallback), and device voices use your system's built-in speech engine. With the AI voice your text is never sent to a server, and each run is limited to 5,000 characters. On the Device voices tab, voices marked "online" may send your text to the browser or OS provider's servers.
With the AI voice, your text and the audio are processed in your browser and are not uploaded to a server. You can check this yourself with a DevTools network test.
How to use (Studio: dialogue, subtitles, background music)
- Paste your script into the "Studio" card under "High-quality AI voice". For a dialogue, write each line as "Name: line".
- Press "Split into sentences", then set each speaker's voice and each sentence's speed, tone and pause. Listen with ▶ and regenerate a sentence with ↻ if needed.
- Optionally add "word=how to read it" lines to the pronunciation dictionary and pick a background music file with its volume and ducking amount.
- Press "Generate all" to make every sentence and join them. If you stop, press it again to continue.
- Download WAV or MP3 plus SRT/VTT subtitles. When you publish, say that it is an AI-generated voice.
How to use (Device voices)
- On the "Device voices" tab, paste the text into the box.
- Choose a voice (from the voices installed on your device), a speed (0.5 to 2.0x) and a pitch (0.5 to 2.0x).
- Press the play button to listen.
- To save the sound as a file, press "Record tab audio (experimental)" and turn on "Share tab audio" in the sharing window, or the sound won't be recorded.
Supported formats and limits
- High-quality AI voice: 31 languages, 5 male and 5 female voices, speed 0.8x-1.5x, quality 4/8/16 steps, up to 5,000 characters (auto-chunked), saves as WAV or MP3, 44.1kHz sample rate
- Device voices: uses the browser's built-in speech synthesis (Web Speech API). The list shows the voices your device and browser provide (some are marked "online"), so it differs from device to device. Speed 0.5x-2.0x, pitch 0.5x-2.0x
- Device voices don't provide a built-in way to save the speech as a file. The experimental "Record tab audio" feature uses screen sharing (with tab audio) to record the speech as a webm file
- The AI voice's model files come from the Dagochim family model storage (models.dagotools.com, or Hugging Face as a fallback) and need about 400MB on first use; after that they're cached in your browser
Open source used
- Supertonic 3 (model weights, OpenRAIL-M license) — Supertone Inc.
- Supertonic inference sample code (MIT license) — Supertone
- ONNX Runtime Web (MIT license) — Microsoft
Tips
- Use "Pre-download" on Wi-Fi the first time so the AI voice is ready to generate audio instantly later.
- Pick 4 steps when you just need a quick result, or 16 steps when naturalness matters most. The default, 8 steps, is a good balance of speed and quality.
- For presentation practice, set the AI voice speed a little slower (0.9-1.0x) than normal speech so you can hear each word clearly.
- If your device has no voice for the language you need, install a voice pack in your operating system settings, or just use the AI voice tab, which needs no installation.
- When you use "Record tab audio", always turn on "Share tab audio" in the sharing window. Otherwise the file may be silent.
Troubleshooting
- If the AI model download is slow or fails, check your connection (or switch to Wi-Fi) and press "Pre-download" again.
- If AI voice generation feels slow, try 4 steps, or your device may not support WebGPU (it then falls back automatically to WASM, which is slower).
- If you see a message that speech synthesis isn't supported, open the page in the latest Chrome, Edge or Safari.
- On the Device voices tab, if it says no English voice was found, your device has no English voice installed. Add one in your operating system settings or try another browser.
- If the recorded file is silent, "Share tab audio" wasn't turned on. Turn it on when you try again.
FAQ
Can I save the speech as an audio file?
Yes. Audio made in the "High-quality AI voice" tab can be saved directly as a WAV or MP3 file. The "Device voices" tab has no built-in save feature, so use the screen-recording method instead.
Which model powers the AI voice?
It runs Supertone's open-source Supertonic 3 model directly in this browser (ONNX Runtime Web). It supports 31 languages and lets you pick from 5 male and 5 female voices.
Does the AI voice need an internet connection?
Only the first time, to download the model files (about 400MB). After that they're cached in this browser, so you can use it right away next time.
Is my text sent to a server?
Not with the High-quality AI voice: your text and the generated audio are processed entirely on this device. Only the model files are downloaded, from the Dagochim family model storage (models.dagotools.com, or the original distributor Hugging Face as a fallback). On the Device voices tab, voices marked "online" may send your text to the browser or OS provider's servers.
Why do device voices look different for different people?
The device voice list comes from the speech engines installed on each device and browser, so it differs from device to device. The AI voice always offers the same 10 voices for everyone.
Can I publish audio made with the AI voice?
Yes, but you must disclose that it's AI-generated, and you can't use it to impersonate someone, create deepfakes, do anything illegal, harass anyone, or spread disinformation. See the OpenRAIL-M license for details.
Can it read several paragraphs at once?
Yes. The AI voice accepts up to 5,000 characters per run; within that limit, long text is split into paragraph-sized chunks automatically, read in order and stitched back together. For more than 5,000 characters, make the rest in another run.
Can I make a dialogue with several speakers?
Yes. In the Studio, write each line as "Name: line" and each name is read with a different voice. You can change a speaker's voice for all of their lines at once or per sentence, and the names also go into the subtitles.
Can I regenerate just one sentence?
Yes. After "Split into sentences", you can set the voice, speed, tone and pause for each sentence and use the ↻ button to regenerate only that one. Unchanged sentences are not regenerated, so it is quick.
Can I download subtitles (SRT/VTT)?
Yes. After generating everything you can download SRT and VTT subtitles along with WAV or MP3. The subtitle times come from where each sentence sits in the final audio, so they line up in a video editor.
Can I add background music?
Yes. Pick a music file from your device and set its volume, how much it drops while someone speaks (dB), fade in and out, and looping. It is lowered by the amount you set during speech and comes back up in pauses longer than 0.4 seconds. Please check the music's copyright yourself.
Can I control how names or English words are pronounced?
Yes. Add "word=how to read it" lines to the pronunciation dictionary (for example GIF=jif or Nguyen=win) and they are replaced before synthesis. The dictionary is saved only on this device. Numbers, dates, units and money are converted to words automatically only for Korean text; in English, write them out the way you want them read (for example "twenty twenty-six" for 2026).
Learn more
For more detail, see the guide: How to Use Text to Speech and Save It as a File.
For developers: Tools That Don't Upload offers a REST API with a free tier (usage limits apply) for data, text, code, PDF and web tasks. Audio processing is not part of the API.
More tips
If the voice you need is missing
The voice list differs by device and browser. If you need an offline voice for a language, add it to your operating system. On Windows you can add voices in the Language or Speech section of Settings (menu names differ by version).
Saving speech as a file
Browser speech synthesis (device voices) is designed to play through your speakers, so it does not provide a way to save the audio as a file. The easiest way to get a file is the tool's "High-quality AI voice" tab: it creates the speech in your browser and saves WAV or MP3 (the model, about 400 MB, downloads the first time). If you want to keep a device voice, here are the alternatives.
- The tool's "Record tab audio (experimental)" option records the sound of the tab you choose when sharing your screen and saves it. You need to turn on tab audio sharing in the sharing window, and it may not work in every browser.
- Use the read-aloud or recording features built into your operating system or phone.
Recording and distributing copyrighted text read aloud can cause problems. Keep it for personal study.