Retrieve text-to-speech history item
Returns metadata for a stored text-to-speech generation.
Authorizations
Gateway auth: send Authorization: Bearer <mka1-api-key>. For multi-user server-side integrations, you can also send X-On-Behalf-Of: <external-user-id>.
Headers
Optional external end-user identifier forwarded by the API gateway.
Path Parameters
Response
OK
A stored text-to-speech generation.
Unique identifier for the history item.
The object type, always 'speech.tts'.
The input text that was synthesized.
The requested language ('auto' or an ISO 639-1 code).
The language actually used for synthesis.
The TTS model used.
The provider that produced the audio.
Audio format of the stored output (wav, mp3, or pcm).
Size of the generated audio in bytes.
-9007199254740991 <= x <= 9007199254740991Number of characters in the input text.
-9007199254740991 <= x <= 9007199254740991Whether the audio was produced via the streaming endpoint.
Arbitrary metadata stored with the item.
Unix timestamp (seconds) when the item was created.
-9007199254740991 <= x <= 9007199254740991