> ## Documentation Index
> Fetch the complete documentation index at: https://docs.verbex.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# List STT providers
> List the speech-to-text providers you can use in an agent, with the models each one offers per language. This catalog is read-only.
To reference an entry when you [create](/api-reference/ai-agents-v3/create-ai-agent) or [update](/api-reference/ai-agents-v3/update-ai-agent) an agent:
| Agent field | Where it is in this response |
| --- | --- |
| `stt.provider_id` | `data[].id` |
| `stt.model_id` | `data[].languages[].models[].id` |
The catalog is global. Providers are sorted by `priority`, then by creation time. Pass `sort_direction` to reverse the order.
## Filters
| Parameter | Notes |
| --- | --- |
| `language_code` | Only providers that support this language code. |
| `status` | `ACTIVE`, `INACTIVE` or `DELETED`. Defaults to `ACTIVE`. |
| `page_size` | `1`–`100`, default `10`. |
| `sort_direction` | `asc` or `desc`, default `desc`. |
This list still uses the older paged shape, not the v3 envelope. The providers are in the top-level `data` array and the cursor is the top-level `next_page_token`. There is no `status` or `message`. When `next_page_token` is absent, you have reached the last page.
## OpenAPI
````yaml /api-reference/openapi.json get /v3/stt/providers
openapi: 3.1.0
info:
title: Verbex Platform API
description: API for managing AI agents, calls, phone numbers, and more.
version: 1.0.0
servers: []
security: []
tags:
- name: Knowledge Bases
description: >-
Create and manage knowledge bases, ingest documents into them, and search
them semantically.
**Authentication.** Every request carries a bearer token: `Authorization:
Bearer `. That is the only credential a client sends. The
gateway resolves your identity from it and injects the tenant headers the
service reads internally, so clients never send `x-user-org-id` or
`x-verbex-id` themselves.
**Tenancy is enforced on every route.** A knowledge base belongs to one
organization and one user. Requesting one your token does not own returns
`404 Knowledge base not found`, never `403`. This is deliberate: a
nonexistent ID, a malformed ID and someone else's ID are indistinguishable
in the response, so the API cannot be used to probe for other tenants'
data. If you get a `404` on an ID you are certain exists, suspect the
token before you suspect the ID.
**Ingestion is asynchronous.** File upload and website crawl both answer
`202` as soon as the material is stored and the job is queued. Parsing,
chunking, embedding and indexing happen afterwards in a worker. Poll the
document status endpoint until it reports `completed` before expecting
search to see the content. That gap is the most common source of "why
isn't my data showing up".
**There is no document update endpoint.** Every submission mints a new
`document_id`, so re-uploading a file or re-crawling the same URLs creates
a second document while the first remains. To refresh material, delete
then resubmit — and note that the sequence is not atomic.
- name: AI Agents v3
description: >-
Create, read, update and delete AI agents. v3 selects the LLM,
speech-to-text model and voice by catalog id, and wraps every response in
a standard envelope. It replaces the deprecated AI Agents v2 operations,
which stop working on November 30, 2026. See [Migrate from v2 to
v3](/api-reference/ai-agents-v3/migrate-from-v2).
- name: LLM Models
description: >-
The LLM model catalog. Look up the `llm_model_id` to send as `llm.llm_id`
when you create or update an agent.
- name: Speech Providers
description: >-
The speech-to-text and text-to-speech provider catalogs. Look up the
`provider_id`, `model_id` and `voice_id` to send when you create or update
an agent.
paths:
/v3/stt/providers:
get:
tags:
- Speech Providers
summary: List STT providers
description: >-
List the speech-to-text providers you can use in an agent, with the
models each one offers per language. This catalog is read-only.
To reference an entry when you
[create](/api-reference/ai-agents-v3/create-ai-agent) or
[update](/api-reference/ai-agents-v3/update-ai-agent) an agent:
| Agent field | Where it is in this response |
| --- | --- |
| `stt.provider_id` | `data[].id` |
| `stt.model_id` | `data[].languages[].models[].id` |
The catalog is global. Providers are sorted by `priority`, then by
creation time. Pass `sort_direction` to reverse the order.
## Filters
| Parameter | Notes |
| --- | --- |
| `language_code` | Only providers that support this language code. |
| `status` | `ACTIVE`, `INACTIVE` or `DELETED`. Defaults to `ACTIVE`. |
| `page_size` | `1`–`100`, default `10`. |
| `sort_direction` | `asc` or `desc`, default `desc`. |
This list still uses the older paged shape, not the v3 envelope. The
providers are in the top-level `data` array and the cursor is the
top-level `next_page_token`. There is no `status` or `message`. When
`next_page_token` is absent, you have reached the last page.
operationId: list_stt_providers_v3
parameters:
- name: language_code
in: query
required: false
description: Only providers that support this language code, for example `en-US`.
schema:
type: string
title: Language Code
- name: status
in: query
required: false
description: Filter by lifecycle status.
schema:
type: string
enum:
- ACTIVE
- INACTIVE
- DELETED
default: ACTIVE
title: Status
- name: page_size
in: query
required: false
description: Number of results per page, `1`–`100`.
schema:
type: integer
minimum: 1
maximum: 100
default: 10
title: Page Size
- name: page_token
in: query
required: false
description: >-
Cursor from the previous response's `next_page_token`. Omit for the
first page.
schema:
type: string
title: Page Token
- name: sort_direction
in: query
required: false
description: Sort order.
schema:
type: string
enum:
- asc
- desc
default: desc
title: Sort Direction
responses:
'200':
description: Page of STT providers
content:
application/json:
schema:
$ref: '#/components/schemas/SttProviderPage'
example:
data:
- id: 6a5c45808d2d94e9d0e255d3
provider_name: deepgram
display_name: Deepgram
status: ACTIVE
priority: 10
languages:
- language_code: en-US
language_name: English (US)
is_default: true
models:
- id: aec2493a-eba9-48d0-9e64-4aab4437f7f5
model_name: nova-2-phonecall
display_name: Nova 2 Phone Call
model_version: '2'
latency_in_ms: 300
tag: telephony
is_default: true
support_interruption_mode: true
created_at: '2026-05-04T08:00:00Z'
modified_at: '2026-09-12T11:20:00Z'
next_page_token: >-
eyJwcmlvcml0eSI6MTAsIl9pZCI6IjZhNWM0NTgwOGQyZDk0ZTlkMGUyNTVkMyJ9
components:
schemas:
SttProviderPage:
type: object
title: PagedResponse
description: >-
This list uses the older paged shape: the array is the top-level `data`,
the cursor is the top-level `next_page_token`, and there is no `status`
or `message`.
properties:
data:
type: array
items:
$ref: '#/components/schemas/SttProvider'
title: Data
description: Providers on this page.
next_page_token:
type: string
title: Next Page Token
description: Cursor for the following page. Omitted on the last page.
SttProvider:
type: object
title: SttProvider
properties:
id:
type: string
title: Id
description: Provider id. Send it as `stt.provider_id`.
provider_name:
type: string
title: Provider Name
description: >-
Provider key, for example `deepgram`. Also the path parameter of the
get operation.
display_name:
anyOf:
- type: string
- type: 'null'
title: Display Name
description: Provider name for display.
status:
type: string
enum:
- ACTIVE
- INACTIVE
- DELETED
title: Status
description: >-
Lifecycle status. Only `ACTIVE` providers can be referenced by an
agent.
priority:
anyOf:
- type: integer
- type: 'null'
title: Priority
description: Sort weight.
created_at:
anyOf:
- type: string
format: date-time
- type: 'null'
title: Created At
description: Creation time.
modified_at:
anyOf:
- type: string
format: date-time
- type: 'null'
title: Modified At
description: Last change time.
languages:
type: array
items:
$ref: '#/components/schemas/SttLanguage'
title: Languages
description: Languages the provider supports.
SttLanguage:
type: object
title: SttLanguage
properties:
language_code:
type: string
title: Language Code
description: BCP-47 language code.
language_name:
anyOf:
- type: string
- type: 'null'
title: Language Name
description: Language name for display.
is_default:
type: boolean
title: Is Default
description: Whether this is the provider's default language.
models:
type: array
items:
$ref: '#/components/schemas/SttModel'
title: Models
description: Models offered for this language.
SttModel:
type: object
title: SttModel
properties:
id:
type: string
title: Id
description: Model id. Send it as `stt.model_id`.
model_name:
type: string
title: Model Name
description: Provider model name, for example `nova-2-phonecall`.
display_name:
anyOf:
- type: string
- type: 'null'
title: Display Name
description: Model name for display.
model_version:
anyOf:
- type: string
- type: 'null'
title: Model Version
description: Model version.
latency_in_ms:
anyOf:
- type: integer
- type: 'null'
title: Latency In Ms
description: Expected latency in milliseconds.
tag:
anyOf:
- type: string
enum:
- fast
- accurate
- balanced
- medical
- telephony
- meeting
- general
- type: 'null'
title: Tag
description: What the model is tuned for.
is_default:
type: boolean
title: Is Default
description: Whether this is the default model for the language.
support_interruption_mode:
type: boolean
title: Support Interruption Mode
description: Whether the model supports the agent's `interruption_mode`.
````
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.