Skip to main content
POST
Synthesize speech for one input via Orpheus-3B

Authorizations

Authorization
string
header
required

The access token received from the authorization server in the OAuth 2.0 flow.

Body

application/json
text
string
required

Text to synthesize.

Required string length: 1 - 2000
speaker_id
string
default:salt_lug_0001

Speaker tag from the Orpheus finetune set (see GET /speakers).

language
string | null

Optional ISO 639-3 language code (e.g. 'lug', 'eng'). If set, speaker_id must belong to it.

seed
integer | null

RNG seed for reproducibility.

temperature
number
default:0.6
Required range: 0 <= x <= 2
top_p
number
default:0.95
Required range: x <= 1
repetition_penalty
number
default:1.1
Required range: 1 <= x <= 2
max_tokens
integer
default:1200
Required range: 64 <= x <= 4096

Response

Successful Response

audio_url
string<uri>
required
Required string length: 1 - 2083
audio_url_expires_at
string<date-time>
required
speaker_id
string
required
duration_seconds
number
required
audio_size_bytes
integer
required
gcs_object
string
required
request_id
string
required
timings_ms
OrpheusTimings · object
required
language
string | null
sample_rate
integer
default:24000
chunks
integer | null