Audio to Text
Turn a recorded conversation into a readable document: who said what, and when
- Paragraphs and speakers
- Timecodes and click-to-seek
- Export to DOCX, PDF, TXT and subtitles
A text-to-speech converter with natural-sounding AI voices. Type or paste any text and listen to it spoken aloud — supports multiple languages, voice styles, and adjustable speed.
Type or paste text into the text area. How much you can voice at once depends on the account: up to 3 000 characters without signing in, up to 30 000 with Premium. Today's exact remaining amount is always shown under the input. You can also drop a .txt file directly.
Pick a language or let the tool detect it — the list narrows to the voices that actually speak it; for the language of this page there are 60 voices. Filter by gender and favorites.
Fine-tune speed, pitch, and speaking style. Insert [pause 3s] between phrases for an exact pause of the length you need.
Click "Generate Speech" — audio plays with real-time word highlighting. Download the result as MP3 or WAV.
Audio to Text
Turn a recorded conversation into a readable document: who said what, and when
Trending right now
Name: text — every speaker gets their own voice below. Lines without a name continue the previous speaker.
Audio is generated by AI. Do not use it to impersonate real people without their consent.
136 voices across 34 languages. For the language of this page — 60 voices; the table below shows how many voices each language has of its own. Another 32 are multilingual and read text in whatever language it is written in.
| Language | Voices | Female | Male |
|---|---|---|---|
| English | 28 | 17 | 11 |
| Chinese | 6 | 3 | 3 |
| Arabic | 4 | 2 | 2 |
| Spanish | 4 | 2 | 2 |
| French | 4 | 2 | 2 |
| Portuguese | 4 | 2 | 2 |
| German | 3 | 2 | 1 |
| Russian | 2 | 1 | 1 |
| Korean | 2 | 1 | 1 |
| Indonesian | 2 | 1 | 1 |
| Italian | 2 | 1 | 1 |
| Japanese | 2 | 1 | 1 |
| Hindi | 2 | 1 | 1 |
| Turkish | 2 | 1 | 1 |
| Dutch | 2 | 1 | 1 |
| Swedish | 2 | 1 | 1 |
| Ukrainian | 2 | 1 | 1 |
| Czech | 2 | 1 | 1 |
| Thai | 2 | 1 | 1 |
| Vietnamese | 2 | 1 | 1 |
| Romanian | 2 | 1 | 1 |
| Danish | 2 | 1 | 1 |
| Norwegian Bokmål | 2 | 1 | 1 |
| Hebrew | 2 | 1 | 1 |
| Malay | 2 | 1 | 1 |
| Filipino | 2 | 1 | 1 |
| Bangla | 2 | 1 | 1 |
| Urdu | 2 | 1 | 1 |
| Persian | 2 | 1 | 1 |
| Tamil | 2 | 1 | 1 |
| Hungarian | 2 | 1 | 1 |
| Polish | 1 | 0 | 1 |
| Greek | 1 | 1 | 0 |
| Finnish | 1 | 0 | 1 |
A voice is picked per language: choosing the language first narrows the list to the voices that actually speak it.
How many characters each voice class gives you, and which of them are open to you, is in the limits table above.
You can earn with this skill
Open an expert page: services, schedule, and client bookings. One form, about ten minutes.
No experts in this category yet — you could be the first.
Pages opened before February 28, 2027 get the “Founding expert” badge.
Audio to Text
Turn a recorded conversation into a readable document: who said what, and when
| Voice type | No account | 👑 Premium account |
|---|---|---|
| HD voices 14 voices · 4 without Premium, 10 with Premium · runs on your device | Premium only | 100 000 per synthesis 700 000 per day |
| Standard 24 voices · 17 without Premium, 7 with Premium · Microsoft servers | 3 000 per synthesis 3 000 per day | 30 000 per synthesis 100 000 per day |
| New 12 voices · our servers | 3 000 per synthesis 3 000 per day | 30 000 per synthesis 100 000 per day |
| OpenAI and Yandex 10 voices · for tokens · provider servers | billed in tokens | billed in tokens |
For the language of this page — 60 voices. Other languages have their own sets.
The daily allowance is shared across all our tools: spend it in the document reader and less is left here. Cloud voices reset at 00:00 UTC, HD voices at your local midnight. OpenAI and Yandex voices (🪙) are billed in tokens and do not count against it.
Tembrica is a text-to-speech tool with studio-quality neural voices in 34+ languages. No sign-up. Automatic language detection, speed and pitch control, voice preview, download as MP3, OGG, or WAV.
136 voices across 34 languages in total, from five sources: Microsoft cloud voices, our own server voices, HD voices rendered by your browser, and studio voices from OpenAI and Yandex billed in tokens. For the language of this page there are 60 voices; every language has its own set — the “Languages and available voices” table below shows how many.
Your text is sent to our server, which connects to Microsoft's neural speech service via a secure WebSocket to generate audio. The text is used only for the duration of the synthesis request.
The limit depends on the account, so there is no single number: without signing in, 3 000 characters per synthesis and 3 000 per day; with Premium, 30 000 per synthesis and 100 000 per day. Your current allowance is always shown under the input, and the field itself truncates text longer than your limit. For longer texts, split them into parts that fit your limit, generate each separately, then join the MP3 files with our audio joiner.
Stress, yes — on the Russian voices that hear it: put the cursor in a word and press “Insert stress”, or type + before the stressed vowel (номер+а). “Auto-stress” marks the whole text and lists the ambiguous words: for «номера» it offers но́мера and номера́. The standard cloud voices place stress themselves and are not sent the mark — it distorts the word. Pauses, yes — and precisely: write [pause 3s] between phrases and the service inserts a pause of exactly that length (0.1 to 30 seconds — handy for workouts, meditation, step-by-step instructions); /pause/ gives a short pause. Emphasizing a single word with markup is not supported on the standard voices — for emotional delivery pick a speaking style in the settings or a premium voice with 'Vibe'.
MP3 for anything you are going to publish or send, WAV if the speech is going into an editor and will be cut, layered or processed further. The speech itself arrives as MP3 at 24 kHz, which is the sample rate the voice was generated at; choosing WAV on download converts that in the page rather than fetching a better original, so it does not add detail that was never there — what it does is stop a second round of lossy encoding when you re-export from your editor. For a podcast or a video, MP3 at the higher bitrate is indistinguishable and a tenth of the size.
Auto-detection works best with sentences (3+ words). For very short text or mixed-language content, select the language manually from the dropdown. The tool detects language by analyzing Unicode script ranges and common word patterns.
Work through it with a specialist — an online lesson or consultation, times shown in your time zone.
We can! Just send us a quick message with your idea. If you'd like to discuss it in detail, leave your email and we'll get back to you. You can stay anonymous.
By uploading content you confirm that you are entitled to disclose its contents to third parties, and you undertake not to include other people's personal data in it. See the Terms of Use for details. AI providers Tembrica is an independent product. We are not affiliated with, endorsed by or sponsored by the makers of the models and services listed here; their names are used only to say factually which engine runs a given tool.
This result was generated by a neural network. Any rights that could arise on our side pass to you — perpetually, with no usage fees and no limits on territory, print run or manner of use, commercial use included. The rights are non-exclusive: another user may obtain a similar result. Crediting Tembrica or linking back is not required. The file carries a machine-readable AI-origin marker in its metadata. More in the Terms of Service
Report a problem or suggest an improvement. We read everything!
Your message has been sent. We will review it shortly.
Оплата через СБП · ₽
Откройте приложение банка, выберите «Оплатить по QR» и наведите камеру на код.
Открыть приложение банкаЖдём подтверждения от банка…
Открыть ссылку на оплату