Skip to main content
PUT

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
kind
enum<string>
required

The job this key does: speech-to-text, LLM or voice.

Available options:
stt,
llm,
tts
provider
enum<string>
required

Who does the job. Speech-to-text: deepgram, assemblyai, soniox, speechmatics, gladia, sarvam, elevenlabs, cartesia, openai, groq, mistral, azure. LLM: openai, anthropic, google, groq, mistral, sarvam, deepseek, xai, together, fireworks, cerebras, openrouter, openai_compatible. Voice: deepgram, elevenlabs, cartesia, openai, sarvam, soniox, mistral, azure, rime, inworld, hume, murf, speechify. A provider that does not do the job is refused with the list that does.

Available options:
deepgram,
assemblyai,
soniox,
speechmatics,
gladia,
sarvam,
elevenlabs,
cartesia,
openai,
groq,
mistral,
azure,
rime,
inworld,
hume,
murf,
speechify,
anthropic,
google,
deepseek,
xai,
together,
fireworks,
cerebras,
openrouter,
openai_compatible
credentials
object
required

The provider's fields. Every provider takes apiKey and an optional model; azure also takes region and optionally endpoint; openai_compatible also takes baseUrl. Any other field is refused.

Response

The key as stored, masked.

One of your own provider keys, masked.

kind
enum<string>
required

Its job: speech-to-text, LLM or voice.

Available options:
stt,
llm,
tts
provider
string
required

The provider's id, e.g. deepgram.

label
string
required

The provider's name as the console shows it.

key
string
required

The key's last four characters after … — never more.

Example:

"…k9z2"

fields
object
required

The key's other settings, as stored: model, region, endpoint or baseUrl. The secret is never among them.

model
string | null
required

The model this key runs, or null while one is still to be chosen (or for a provider with no model to choose, such as Azure Speech).

models
string[]
required

What the provider offered this key when it was added or last refreshed.

verifiedAt
string<date-time> | null
required

When the provider last accepted the key.

updatedAt
string<date-time>
required

When the key or its model last changed.