Skip to main content
GET
Get a text-to-speech model

Path Parameters

author
string
required

Model author/organization

Example:

"openai"

slug
string
required

Model slug

Example:

"gpt-4o-mini-tts"

Response

A text-to-speech model and its endpoints

A text-to-speech model. Its members are the envelope of its endpoints': enums are unioned and ranges widened, so a value inside a range may be accepted by no single endpoint. Each record in endpoints lists exactly what that endpoint accepts.

created
integer
required

Unix timestamp (seconds) of when the model was created

description
string
required
endpoints
object[]
required

Each endpoint serving the model, with exactly the inputs and parameters it accepts. Some endpoints route only after the caller accepts a provider requirement such as a self-attestation; until then, a request to them is rejected with a 403 that names the requirement.

id
string
required

Model slug

Example:

"openai/gpt-4o-mini-tts"

input_modalities
object[]
required

An input the model accepts. audio and image are input_references for voice cloning and voice design.

Example:
name
string
required
Example:

"OpenAI: GPT-4o mini TTS"

output_modalities
object[]
required