Self-hosted · 5 languages · no per-word fees

Give your words a voice.

Type anything, pick a language and a voice, and hear it in seconds — English, Spanish, German, Italian, and Hebrew. Natural 44.1 kHz audio from a self-hosted neural model. No API keys, no metering surprises.

voicewright · studio ● ready
0 / 600
Free · up to 600 characters per clip
↓ WAV
44.1 kHz studio audio Hebrew + 4 more languages ~0.2× real-time on CPU MIT-licensed engine

From text to voice in one step

No accounts to wire up, no cloud credits to buy. The model runs on our own hardware, so every clip costs us near-zero — and that saving is why there are no per-word fees.

01

Type or paste

Up to 5,000 characters. Mix languages inline with tags like <he>…</he>.

02

Pick voice & speed

Two studio voices, five languages, adjustable pace. Hebrew renders right-to-left automatically.

03

Listen & download

Hear it instantly, see the waveform, download clean WAV for your video, course, or app.

Five languages, one voice engine

Including the market ElevenLabs serves worst — Hebrew. Audiobooks, news readers, IVR, and ads that finally sound native.

Englishen
Españoles
Deutschde
Italianoit
עבריתhe

Pricing that doesn't meter every word

Because it's self-hosted, the marginal cost of a clip is basically electricity. Start free; upgrade for long-form, an API, and voice cloning.

Free

$0
  • 600 chars / clip
  • All 5 languages
  • 2 studio voices
  • WAV download
Use it now
Popular

Creator

$9/mo
  • 5,000 chars / clip
  • Priority queue
  • MP3 + WAV
  • Commercial license
Start Creator

Pro

$29/mo
  • Long-form (books)
  • REST API access
  • Voice cloning (beta)
  • Priority support
Go Pro

API credits

Pay/use
  • Metered characters
  • Bulk + batch
  • Self-host license
  • Volume pricing
Get credits

Questions

Is this really self-hosted? +

Yes. The neural model (ONNX) runs on our own server — no third-party TTS API is called, so there are no per-word charges and your text isn't sent to a vendor.

Can I use the audio commercially? +

Yes on paid plans. The underlying engine and voices are MIT-licensed with no output-attribution requirement.

How good is the Hebrew? +

Hebrew uses a dedicated diacritization (Renikud) step for correct pronunciation — try it in the studio above and judge for yourself.

Do you offer an API? +

Yes on Pro and API-credits plans — a simple POST /api/tts returns a WAV. See the live API docs.