Coming Soon — Instant voice cloning examples are under development and will be added shortly.
Clone any voice from a short audio sample (5–15 seconds) and use it for text-to-speech synthesis.
- Instant Clone — Upload a short audio clip, get a usable voice ID back
- Clone and Speak — End-to-end: clone a voice then synthesize speech with it
- Manage Cloned Voices — List, preview, and delete your cloned voices
You can clone voices today via the Smallest AI platform or the Python SDK:
from smallestai.waves import WavesClient
client = WavesClient(api_key="YOUR_API_KEY")
voice = client.add_voice("My Custom Voice", "sample.wav")
print(f"Voice ID: {voice}")