Docs Book a Demo Sign in
Text to speech

Russian text to speech, по-русски.

Text to speech in Russian for announcements, reminders, narration and customer messages, in a female and a male voice.

Listen

Two voices, in Russian.

  • Female

    Здравствуйте, чем я могу вам сегодня помочь?

  • Male

    Здравствуйте, чем я могу вам сегодня помочь?

Versa’s output for exactly the text shown, unedited, the same sentence in each of the two voices. The take was checked with a speech recogniser. Measured on eight Russian sentences, an independent recogniser scored a character error of 3.1%.

The voices are speakers from open speech corpora: Russian LibriSpeech (OpenSLR 96), from LibriVox audiobooks (public domain in the USA). All credits.

How it works

Text in, Russian out.

Text to speech turns written Russian into spoken audio. Ours is Versa, a speech model we train ourselves: it generates speech one 70 ms frame at a time, so the first audio arrives in about 25 ms for a single request and the rest streams behind it.

Versa speaks Russian in a female and a male voice, or in a voice cloned from a few seconds of Russian audio. A voice agent can speak Russian, but our speech recognition does not understand it yet, so it cannot hold a two-way conversation in it.

  • VoicesA female and a male voice, both native to Russian.
  • Your voiceA new voice from 3 to 30 seconds of speech, no training.
  • Price$4.10 per million characters, prepaid, no plan.
  • Voice agentsAgents can speak Russian; they do not understand it yet.
The API

One request.

terminal
curl -X POST "https://api.lokutor.com/tts/synthesize" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Здравствуйте, чем я могу вам сегодня помочь?","voice":"ru_f1","language":"ru"}' \
  --output speech.wav
speak.py
import requests

r = requests.post(
    "https://api.lokutor.com/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"text": "Здравствуйте, чем я могу вам сегодня помочь?", "voice": "ru_f1", "language": "ru"},
)
open("speech.wav", "wb").write(r.content)

Returns a WAV file. For streaming, use the WebSocket API or the JavaScript and Python SDKs.

FAQ

Common questions.

How much does Russian text to speech cost?

$4.10 per million characters, the same in every language, billed per character from a prepaid balance. New accounts get $5 of credit with no card, about 1.2 million characters.

Which voices speak Russian?

Russian has a female and a male voice of its own. Any new voice you clone speaks Russian too.

Can I clone a voice in Russian?

Yes. Record or upload 3 to 30 seconds of speech in the dashboard and the new voice speaks Russian and the other 12 languages. Only clone a voice you own or have permission to use.

Can a voice agent hold a conversation in Russian?

Not a two-way one yet. A Lokutor voice agent can speak Russian, but our speech recognition does not understand it yet, so the caller cannot be answered in Russian. Agents hold full conversations in Spanish, Catalan, Galician, Basque, English, Portuguese, French, Italian and German.

Other languages

Spanish · Catalan · Galician · Basque · English · Portuguese · French · Italian · German · Dutch · Polish · Romanian

Hear your own text.

$5 of credit to start, no card. Type it in the speech studio and press play.