Create Voice | SpeechifyAI API

Create a cloned voice for the workspace from a 10-30 second audio sample, with verified consent from the speaker.

Cloning requires proof that the speaker agreed to it. Create a consent challenge with POST /v1/voices/consent-challenges, show the returned phrase to the speaker, record them reading it aloud, and send that recording here as consent_recording together with the challenge’s consent_challenge_id. Speechify transcribes the recording, checks it against the phrase it issued, checks that its speaker is the speaker in your sample, and keeps it as the consent record for the voice. The person consenting therefore has to be the person being cloned. A challenge is single use and short-lived, so record and submit in one sitting.

The clone belongs to the workspace rather than the member who created it, and access follows the caller’s workspace role and API-key scopes exactly as for any other voice: voices scopes to list it, audio scopes to synthesize with it, and the content-management permission plus a write scope on the key to delete it. Cloned voices are usable self-serve on simba-3.0, simba-english and simba-multilingual. simba-3.2 also serves cloned voices, currently as a limited release enabled per workspace; contact Speechify to have it enabled for yours.

Callers pinned before Speechify-Version: 2026-09-13 use the previous flow instead: no challenge, and a consent form field carrying the speaker’s name and email as a JSON string. That flow is deprecated and will be removed after a sunset window announced in the changelog.

Create a cloned voice for the workspace from a 10-30 second audio sample, with verified consent from the speaker. Cloning requires proof that the speaker agreed to it. Create a consent challenge with `POST /v1/voices/consent-challenges`, show the returned `phrase` to the speaker, record them reading it aloud, and send that recording here as `consent_recording` together with the challenge's `consent_challenge_id`. Speechify transcribes the recording, checks it against the phrase it issued, checks that its speaker is the speaker in your `sample`, and keeps it as the consent record for the voice. The person consenting therefore has to be the person being cloned. A challenge is single use and short-lived, so record and submit in one sitting. The clone belongs to the workspace rather than the member who created it, and access follows the caller's workspace role and API-key scopes exactly as for any other voice: voices scopes to list it, audio scopes to synthesize with it, and the content-management permission plus a write scope on the key to delete it. Cloned voices are usable self-serve on `simba-3.0`, `simba-english` and `simba-multilingual`. `simba-3.2` also serves cloned voices, currently as a limited release enabled per workspace; contact Speechify to have it enabled for yours. Callers pinned before `Speechify-Version: 2026-09-13` use the previous flow instead: no challenge, and a `consent` form field carrying the speaker's name and email as a JSON string. That flow is deprecated and will be removed after a sunset window announced in the changelog.

Authentication

AuthorizationBearer

Enter your API key with the Bearer prefix, e.g. ‘Bearer sk_…’.

Headers

Idempotency-KeystringOptional<=255 characters

A client-generated key (an opaque string, max 255 chars) that makes a side-effect POST safe to retry: the server runs the operation exactly once and replays the first response (its status and body) for 24 hours. Reusing a key with a different request body, or while the first request is still in flight, returns 409 idempotency_conflict. A replayed response carries the Idempotent-Replayed: true header.

A client-generated key (an opaque string, max 255 chars) that makes a side-effect POST safe to retry: the server runs the operation exactly once and replays the first response (its status and body) for 24 hours. Reusing a key with a different request body, or while the first request is still in flight, returns `409 idempotency_conflict`. A replayed response carries the `Idempotent-Replayed: true` header.

Request

This endpoint expects a multipart form with multiple files.

namestringRequired

Name of the personal voice

localestringOptionalDefaults to en-US

Native language (locale) of the personal voice (e.g. en-US, es-ES, etc.)

genderenumRequired

Gender marker for the personal voice male GenderMale female GenderFemale not_specified GenderNotSpecified

Allowed values:

samplefileRequired

Audio sample of the voice to clone, 10-30 seconds of clean speech.

avatarfileOptional

Avatar image file

consent_challenge_idstringRequired

The id of the consent challenge this create consumes, from POST /v1/voices/consent-challenges. Single use: once a create has consumed it, whether or not that create succeeded, it cannot be used again.

consent_recordingfileRequired

Recording of the speaker reading the challenge’s phrase aloud. This is the consent record for the voice, not a second voice sample: it must be the same person as in sample, and it is retained as evidence. 5-30 seconds, at most 25 MB, in any common audio container.

Response headers

Speechify-Request-IdstringOptional

Unique identifier for this request, present on every response (2xx and non-2xx alike). If the caller sends a Speechify-Request-Id request header the server echoes it back (sanitized and length-capped) so one logical request can be traced end-to-end; otherwise the server generates a fresh value. Log it on every response and quote it in support requests

it is the stable handle that ties your observation to Speechify’s server-side logs, and it matches the request_id field in the error envelope.

The legacy alias X-Request-ID carries the same value and is still accepted on requests, until 2027-07-24. Prefer the un-prefixed name (RFC 6648).

Unique identifier for this request, present on every response (2xx and non-2xx alike). If the caller sends a `Speechify-Request-Id` request header the server echoes it back (sanitized and length-capped) so one logical request can be traced end-to-end; otherwise the server generates a fresh value. Log it on every response and quote it in support requests - it is the stable handle that ties your observation to Speechify's server-side logs, and it matches the `request_id` field in the error envelope. The legacy alias `X-Request-ID` carries the same value and is still accepted on requests, until 2027-07-24. Prefer the un-prefixed name (RFC 6648).

RateLimit-Limitinteger

Request-rate budget: the maximum number of requests in the current window (the bucket capacity). The IETF-draft un-prefixed name; the legacy alias X-RateLimit-Limit carries the same value. Rides every response.

RateLimit-Remaininginteger

Request-rate budget: requests left in the current window. Legacy alias: X-RateLimit-Remaining.

RateLimit-Resetinteger

Request-rate budget: integer delta-seconds until the window fully refills (same unit as Retry-After). Legacy alias: X-RateLimit-Reset.

Response

A created voice

display_namestring

genderenum

localestring

idstring

modelslist of objects

typeenum

avatar_imagestring or nullOptional

preview_audiostring or nullOptional

tagslist of strings or nullOptional

Errors

400

Bad Request Error

401

Unauthorized Error

402

Payment Required Error

403

Forbidden Error

409

Conflict Error

413

Content Too Large Error

422

Unprocessable Entity Error

429

Too Many Requests Error

500

Internal Server Error

502

Bad Gateway Error

503

Service Unavailable Error

1	from speechify import Speechify
2
3	client = Speechify(
4	token="YOUR_TOKEN_HERE",
5	)
6
7	client.voices.create(
8	sample="example_sample",
9	avatar="example_avatar",
10	)

1	{
2	"display_name": "Example name",
3	"gender": "male",
4	"locale": "en-US",
5	"id": "scott",
6	"models": [
7	{
8	"languages": [],
9	"name": "simba-english"
10	}
11	],
12	"type": "shared",
13	"avatar_image": "example",
14	"preview_audio": "example",
15	"tags": [
16	"example"
17	]
18	}