POST
Create Speech
Returns audio bytes in the requested response_format (Content-Type set accordingly), or Server-Sent speech.audio.delta events when stream_format="sse". voice accepts a model preset, an OpenAI voice name (mapped to the model default), or a cloned ev_* id on cloning-capable models.

Authorizations

Authorization
string
header
required

An EESI API key (sk-eesi-...) or a Clerk session token.

Headers

authorization
string | null
X-API-Key
string | null

Body

application/json
model
string
required
input
string
required
Required string length: 1 - 4096
voice
string
required
response_format
enum<string>
default:mp3
Available options:
mp3,
opus,
aac,
flac,
wav,
pcm
speed
number
default:1
Required range: 0.25 <= x <= 4
stream_format
enum<string>
default:audio
Available options:
audio,
sse
instructions
string | null
language
string | null
normalize_text
boolean
default:false

Response

Successful Response