Start building
with LMNT
Everything you need to integrate LMNT's fast, lifelike, and affordable speech models into your applications. From first steps to production.
import asyncio
from lmnt import AsyncLmnt
async def main():
client = AsyncLmnt()
async with client.speech.with_streaming_response.generate(
text=(
"Uhh, did you see the weather in Palo Alto tomorrow? "
"Yeah, can't believe it's gonna rain, dude. Like what?"
),
voice='leah',
) as response:
await response.stream_to_file('hello.mp3')
asyncio.run(main())
Platform
Choose how you build
Pick the surface that matches the type of integration you're building.
Generate speech
Turn text into speech. In any voice, in any of our 24 languages.
Your LLM + LMNT
Generate speech in realtime with your favorite LLM, at scale.
Developer journey
From idea to production
Follow the lifecycle or jump to what you need.
Models
Meet our model
Our research & engineering, packaged up and serving on our optimized infra.
Blizzard 1.4
Excels at low-latency, voice cloning, accents, styles, and languages.
Resources