Skip to main content
POST
Synthesize speech from text (TTS)

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
string
required
text
string
required
Maximum string length: 5000
voice_id
string
language
string
speed
number
Required range: 0.5 <= x <= 2

Response

Speech synthesized. Audio returned in outputs with a signed URL.

id
string
object
enum<string>
Available options:
generation
status
enum<string>
Available options:
queued,
running,
succeeded,
failed,
canceled
modality
enum<string>
Available options:
image,
video,
voice,
music,
avatar,
chat,
3d,
upscale
prompt
string
params
object
reserved_credits
integer
charged_credits
integer
refunded_credits
integer
cache_hit
boolean
outputs
object[]