English text to speech, in English.

Two voices, in English.

• Emma

  Hi, I'm calling from the clinic to confirm your appointment tomorrow at half past ten. Does that still work for you, or would another time be better?

• Lucas

  Your order left our warehouse this morning and should arrive on Thursday. If you need to change the delivery address, I can do that for you right now.

Versa 2.0’s output for exactly the text shown, through the public API, unedited.

Text in, English out.

Text to speech turns written English into spoken audio. Ours is Versa, a speech model we train ourselves: it generates each chunk of sound in parallel instead of one token at a time, so the first audio arrives in about 65 ms and the rest streams behind it.

Any of the ten voices speaks English, and so does any voice you clone, whatever language it was recorded in.

• VoicesTen built in, and all of them speak English.
• Your voiceA new voice from 3 to 30 seconds of speech, no training.
• Price$4.10 per million characters, prepaid, no plan.
• Voice agentsAgents listen and answer in English, on the web or the phone.

One request.

curl -X POST "https://api.lokutor.com/tts/synthesize" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hi, how can I help you today?","voice":"F3","language":"en"}' \
  --output speech.wav

import requests

r = requests.post(
    "https://api.lokutor.com/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"text": "Hi, how can I help you today?", "voice": "F3", "language": "en"},
)
open("speech.wav", "wb").write(r.content)

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

Spanish · Catalan · Galician · Basque · Portuguese · French · Italian · German