Render text to speech with timing information and subtitles

post

https://api.wellsaidlabs.com/v1/tts/word-timing

This method takes text input and generates an audio clip, along with word timing data. Word timing output includes word level timing in a json file, an srt file, and vtt file.

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Body Params

speaker_id

integer

enum

required

text

string

required

length between 1 and 1000

model

string

enum

Which model to use. Note that not all voices are available on all models.

Allowed:

library_ids

array of strings

List of ids of replacement libraries to use when processing

library_ids

audio_configs

object

Headers

X-Enable-SSML

boolean

Enables limited SSML translation for input text

string

enum

Defaults to application/json

Generated from available response content types

Allowed:

Responses

200A zip file containing the generated audio, as well as word timing files.

400Request failed input validation

401API key is missing or invalid

429Rate limit or concurrency limit has been exceeded

508Request render loop detected. This is likely a result of unusual phrasing, characters, and/or punctuation. The recommended action is to modify the input and retry.