French text to speech, en français.

Two voices, in French.

• Maria

  Bonjour, je vous appelle de la clinique pour confirmer votre rendez-vous de demain à dix heures et demie. Cela vous convient toujours, ou préférez-vous un autre horaire ?

• Oliver

  Votre commande a quitté notre entrepôt ce matin et devrait arriver jeudi. Si vous devez changer l'adresse de livraison, je peux le faire tout de suite.

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

Text in, French out.

Text to speech turns written French 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.

Every voice speaks French, and a voice agent can listen and answer in French on the web or on the phone.

• VoicesTen built in, and all of them speak French.
• 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 French, 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":"Bonjour, comment puis-je vous aider ?","voice":"F4","language":"fr"}' \
  --output speech.wav

import requests

r = requests.post(
    "https://api.lokutor.com/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={"text": "Bonjour, comment puis-je vous aider ?", "voice": "F4", "language": "fr"},
)
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 · English · Portuguese · Italian · German