API Reference
These docs are for v1.0. Click to read the latest docs for v2.0.

Returns time annotations for each word.

post
https://v2.api.audio/speech/tts/annotate

Returns timestamps, or time in seconds, when each word is spoken for a given generated speech file. You only need to provide a SpeechID in order to receive an annotation of the relevant time annotations.

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Body Params

Get a list of words and its time annotations, either timestamps or seconds

string
required

Speech ID for the speech file you want to annotate.

string

languageCode (ISO 639-1 standard) of the speech file. If not provided, we try to detect the language.

Response

Updated 7 months ago

Language
Credentials
Header
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json

Updated 7 months ago