Create a Sample

post

https://app.coqui.ai/api/v2/samples

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

If you set the format query argument to wav or the Accept header to audio/wav, this request will redirect you immediately to the synthesized audio file, rather than returning the JSON metadata with audio URL. The metadata will still be created and available via the List Samples endpoint. Make sure your client or HTTP request library is set up to follow redirects!

Streaming download/playback example

A Python script which does text-to-speech using XTTS and streams the audio download/playback is available here: https://gist.github.com/reuben/5f483772864c1ac9687ba1c7aa3cb11f

Query Params

format

string

enum

Allowed:

Body Params

speaker_id

uuid

deprecated

ID of a Speaker to use for rendering this sample. Deprecated, use voice_id instead.

voice_id

uuid

ID of a Speaker or Voice object to use for rendering this sample.

emotion

string

enum

Defaults to Neutral

Neutral - Neutral
Happy - Happy
Sad - Sad
Surprise - Surprise
Angry - Angry
Dull - Dull

Allowed:

name

string

length between 1 and 120

Name of sample. Optional, to be used for your own bookkeeping purposes.

text

string

required

length between 1 and 500

Text to be synthesized.

speed

double

0 to 2

Defaults to 1

Pronunciation speed of synthesized audio. From 0 = slowest to 2 = fastest.

Headers

string

enum

Defaults to application/json

Generated from available response content types

Allowed:

content-type

string

enum

Defaults to application/json

Generated from available request content types

Allowed:

Responses

400

No response body

401

No response body

Streaming download/playback example

201

403

404