Skip to main content
POST
Create audio generation
See the Audio API guide for request examples, limits, billing and delivery behavior. Use mode: "text_to_speech" for single-speaker speech or follow Text to Dialogue for multi-speaker input. Both modes use this endpoint and the same task lifecycle.

Authorizations

Authorization
string
header
required

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

Headers

Idempotency-Key
string

Reuse the same key and body after a timeout to recover accepted work without generating or charging twice.

Required string length: 1 - 128

Body

application/json
model
enum<string>
required
Available options:
eleven_v3,
eleven_v4,
eleven_v4_turbo
mode
enum<string>
default:text_to_speech
Available options:
text_to_speech,
text_to_dialogue
prompt
string

Speech text. Maximum 2,000 Unicode code points including whitespace and tags across the request.

dialogue
object[]

v3/v4 only; at most ten distinct voices. Omit prompt and controls.voiceId.

Maximum array length: 100
controls
object
providerOptions
object
webhookEndpointId
string

Response

Success

id
string
required
model
enum<string>
required
Available options:
eleven_v3,
eleven_v4,
eleven_v4_turbo
status
enum<string>
required
Available options:
queued,
processing,
succeeded,
failed,
cancelled
outputs
object
required
usage
object
phase
string
createdAt
string<date-time>
updatedAt
string<date-time>