All models · Pricing · API docs

espeech-tts API

ESpeech (F5 + RUAccent), our own GPUs — Russian speech with CORRECT stress: places stress and resolves homographs from context (за́мок/замо́к). Auto-enabled for language=Russian on /v1/audio/speech (other languages use Qwen3-TTS). Manual stress — '+' before the vowel (зам+ок)

Runs on our own GPUs in Russia.

How to connect: change one line — base_url. Get an sk- key in the dashboard.

curl https://api.neuraldeep.ru/v1/audio/speech \
  -H "Authorization: Bearer $NEURALDEEP_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"espeech-tts","input":"Hello","voice":"serena"}' -o speech.wav

https://neuraldeep.ru/en/models/espeech-tts