Skip to main content
POST
Preview BYOK Voice

Authorizations

Authorization
string
header
required

Your API key (ta_live_…) from Settings → API keys, sent as Authorization: Bearer <key>. Keep it on a server: it can message every customer you have. A key is full, build or read-only; a request its level does not allow is refused with 403.

Headers

Thinnest-Workspace
string

Developers only: the customer workspace this request acts in — its org_… id from POST /customers. Leave it out to act in your own workspace. Refused with 404 (Workspace not found.) when the id is unknown, is not one of your customers, or is not an org_… id; 410 when that customer was deleted (restore it with POST /customers/{id}/restore until it is erased); 403 when the key belongs to one customer workspace (it cannot act as another); 400 when your workspace is not a developer workspace. /customers/* and GET /customers/usage are your own workspace's and refuse the header with 400: call them without it.

Example:

"org_3fKq9TzQ1mN8vB2xR7cLpA"

Body

application/json
voice
string
required

A voice id from List BYOK Voices.

Maximum string length: 160
agentId
string | null

An agent (ag_…) whose language the line is spoken in when you send no language.

text
string

The line to speak, up to 200 characters. Left out, a short greeting of ours.

Maximum string length: 200
language
string

A language tag such as hi-IN or en, for the line and the voice.

Pattern: ^[A-Za-z]{2,3}([-_][A-Za-z]{2,4})?$
speed
number

Cartesia only. The speed to hear.

Required range: 0.6 <= x <= 1.5
volume
number

Cartesia only. The volume to hear.

Required range: 0.5 <= x <= 2
emotion
string

Cartesia only. One of Cartesia's emotions (English only).

model
enum<string>

Cartesia only. A Sonic model other than your key's.

Available options:
sonic-3.6,
sonic-3.6-2026-08-27,
sonic-3.5,
sonic-3,
sonic-2
pronunciationDictId
string

Cartesia only. A pronunciation dictionary of your account.

Pattern: ^[A-Za-z0-9][A-Za-z0-9_-]{2,79}$

Response

The spoken line. audio/mpeg from most providers; audio/wav from some (Sarvam). Cacheable privately for an hour.

The audio of the spoken line.