Real-time text-to-speech, built for voice agents.
~22 hours of audio for $5. Millisecond time-to-first-chunk. One API call away.
Currently supported:
American EnglishBritish EnglishMexican SpanishBrazilian PortugueseDutch
$5
per 1,000,000 characters
≈ 22 hours of audio · ≈ $0.23/hour
<100 ms
streaming time-to-first-chunk
On GPU; end-to-end also depends on your network/region.
Hear it now
Type something and generate speech, right here. No account needed.
Get your API key
Free credits to start · No credit card required · Open-source model