Skip to main content
POST
Generate speech (unified TTS endpoint)

Authorizations

Authorization
string
header
required

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

Body

application/json

Text-to-speech request for the RunPod Orpheus-3B endpoint.

text
string
required

Text to synthesize.

Minimum string length: 1
voice
string | null

Orpheus speaker catalog tag (e.g. 'salt_lug_0001'). If omitted, a speaker is chosen for language (Luganda by default).

response_mode
enum<string>
default:url

url (signed GCS URL), stream (raw audio bytes from RunPod), or both (raw audio bytes with the signed URL in the X-Audio-Url header).

Available options:
url,
stream,
both
language
string | null

ISO 639-3 code (e.g. 'lug').

temperature
number | null

Sampling knob.

top_p
number | null

Sampling knob.

repetition_penalty
number | null

Sampling knob.

max_tokens
integer | null

Max tokens per chunk.

seed
integer | null

Deterministic seed.

Response

Successful Response

Normalized response for response_mode='url' across all providers.

audio_url
string
required

Signed URL to the generated audio.

model
string
required

Model used.

platform
string
required

Platform used.

voice
string
required

Resolved voice/speaker.

audio_url_expires_at
string<date-time> | null
language
string | null
sample_rate
integer | null
duration_seconds
number | null
gcs_object
string | null
request_id
string | null
timings_ms
Timings Ms · object | null
usage
SpeechUsage · object | null

Usage for this synthesis (characters, bytes, seconds).