On air
Now playing
Booth v3
///
New
32 languages
///
Latency
300 ms to first audio
///
Studio
Dubbing for video, now in beta
///
On air / Take 04 / Mara, EN
The voice layer for every product, script and agent.
Text to speech, voice cloning, dubbing and real time voice agents. One API, 32 languages, voices that breathe.
00:12.48 / 00:31.02
48 kHz / stereo / v3
NORTHWAVE
Halcyon
parcel.fm
KITE/LAB
Ostrava
loudhouse
Text to speech
01
Write it once, hear it in any voice. Paste a script, pick a voice and press play. Booth reads it back with the pauses, breaths and pacing of a real take.
Speech
Clone
Dub
Agents
On air
Good evening. You are listening to the late edition, read by a voice that was never in the room.
Voice
Mara
Stability
62
Clarity
80
Style
35
Voice library
02
Three thousand voices. Or bring your own from one minute of audio.
Control room
03
From one podcast to a million calls. The same API runs a side project and a contact center, and you can watch it work.
Where creators
dub in 32 languages
Ch 01 / Dub
EN
DE
ES
FR
IT
PT
PL
CS
SK
HU
JA
KO
ZH
AR
HI
TR
NL
SV
FI
DA
NO
RO
UK
EL
HE
ID
MS
TH
VI
FIL
TA
BN
32
Now speaking: Japanese. One voice keeps its tone across every language you ship.
Where agents
answer in 300 ms
300ms
0 ms / Request
300 ms / First audio
500 ms
Where studios
ship every week
Hours generated
1
,
2
0
4
,
3
8
8
Uptime / 90 days
99.99%
1 incident / 4 min
Booth / Take 05 / Your turn
Press
record.
Ten thousand free characters a month. No card, no call, no waiting list.