> ## Documentation Index > Fetch the complete documentation index at: https://docs.vocily.ai/llms.txt > Use this file to discover all available pages before exploring further. # Transcribers > The speech-recognition models you can put in `transcriber.model`. `response_speed_seconds` gives the typical wait from the caller's last word to text in hand, per preset, **for that model** — the same preset costs more on one engine than another. It is **`null` on a model that answers on confidence rather than on a clock**: the preset still applies there and still matters, but no number describes it, so none is given. Check for `null` before reading a preset off it. Its four keys are the four presets `conversation.response_eagerness` accepts, and nothing else is a valid value: | Preset | Send as | Meaning | | ---------- | ------- | ------------------------------------------------------------------ | | Fast | `1` | Least patient. Short answers and quick confirmations. | | Responsive | `0.75` | Everyday conversations. | | Balanced | `0.5` | The default. | | Patient | `0` | Callers who pause mid-sentence, or read out numbers and addresses. | The field is a number because that is what it is stored as, but only these four numbers exist — a value like `0.3` is rejected rather than rounded, so what you send is always what the call does. `languages` is what the model can recognise. Every language in an agent's set must be covered, or the agent is refused on save. ## OpenAPI ````yaml developers/openapi.json GET /v1/transcribers openapi: 3.1.0 info: title: Vocily API description: >- Public REST API for Vocily. Build and configure an agent, publish a version and put it live, place outbound calls, and read back calls, chats and what the agent remembered. Authenticate with a workspace API key as a Bearer token. Some things stay in the dashboard, by design: creating an API key, buying or connecting a phone number, setting an agent's webhook URL, connecting WhatsApp and its templates, building HTTP tools, and running batch campaigns. version: v1 servers: - url: https://api.vocily.ai description: Production security: [] paths: /v1/transcribers: get: tags: - catalogues summary: List Transcribers description: >- Speech models you can put in `transcriber.model`. Which component performs end-of-turn detection — ours or the model's own — is not published: it is an implementation detail that changes with the roster (field review E1). `conversation.response_eagerness` applies on every model here. How it LANDS differs: most models take it as how long to wait, and a model that runs its own end-of-turn detector takes it as a confidence threshold for that detector instead. Either way the setting matters, which is why it is offered everywhere — but `response_speed_seconds` describes only the first kind, because the second answers on its own confidence rather than on a clock of ours. `response_speed_seconds` is keyed by preset NAME while the field itself takes the preset NUMBER: `fast` is `1`, `responsive` `0.75`, `balanced` `0.5`, `patient` `0`. The pairing is the same for every model, so it is stated once in the field's own description rather than repeated on all six rows here — the same reason the TTS model name sits on `GET /v1/tts-capabilities` and not on every `GET /v1/voices` row (field review Q9.9, Q16). operationId: list_transcribers_v1_transcribers_get parameters: [] responses: '200': description: Speech models you can put in `transcriber.model`. content: application/json: schema: type: array items: type: object properties: provider: type: string enum: - sarvam - deepgram - soniox model: type: string description: What goes in `transcriber.model`. label: type: string languages: type: array items: type: string description: >- Every language in an agent's set must be covered, or the agent is refused on save. response_speed_seconds: type: object additionalProperties: type: number nullable: true description: >- Typical caller-stops-to-text seconds per response_eagerness preset, for THIS model. **Null on a model that answers on confidence rather than on a clock** — the preset still applies there, but no number describes it, so none is given. Check for null before reading a preset off it. example: - provider: soniox model: soniox label: Soniox languages: - bn-IN - de-DE response_speed_seconds: fast: 0.45 responsive: 0.75 balanced: 1.05 patient: 1.65 - provider: deepgram model: nova-2 label: Nova 2 languages: - de-DE - en-GB response_speed_seconds: fast: 0.6 responsive: 0.65 balanced: 0.75 patient: 0.85 '401': description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/ApiError' example: detail: Invalid API key code: UNAUTHORIZED '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' '429': description: Rate limit exceeded — honor `Retry-After`. content: application/json: schema: $ref: '#/components/schemas/ApiError' example: code: rate_limited security: - bearerAuth: [] components: schemas: ApiError: type: object description: >- Error envelope. `code` is derived from the HTTP status, so branch on it for the CLASS of failure; the specific reason is `detail.code`. Every public refusal carries both. properties: detail: type: object description: >- The reason. `code` is the domain reason (e.g. `call_not_found`) and `message` is a sentence safe to log. On a `422` it also carries `errors[]`, one entry per rejected field — see `HTTPValidationError`. properties: code: type: string example: call_not_found message: type: string example: Call not found required: - code - message code: type: string description: Derived from the HTTP status, not the domain reason. example: NOT_FOUND HTTPValidationError: type: object title: HTTPValidationError description: >- A request the API could not read: a field of the wrong type, out of range, missing, or one we do not accept. Same envelope as every other error. properties: detail: type: object description: >- What was wrong, as `code`, a one-line `message`, and every offending field in `errors`. required: - code - message - errors properties: code: type: string enum: - validation_error message: type: string description: >- The first problem in one line, with a count of the rest — e.g. `model.temperature: Input should be less than or equal to 2 (and 1 more)`. errors: type: array items: $ref: '#/components/schemas/ValidationError' description: >- One entry per offending field. **Every problem is reported at once**, not just the first, so a malformed body needs one round trip to fix rather than one per field. code: type: string enum: - VALIDATION_ERROR description: Derived from the HTTP status, as on every error. ValidationError: type: object title: ValidationError required: - field - message - type properties: field: type: string description: >- The offending field as a path from the root of your request — `voice.speed`, `variables[0].key`, or `query.limit` for a query parameter. **This is the field to read.** message: type: string description: What is wrong with it, in plain language. type: type: string description: >- A stable machine code for the kind of failure, e.g. `extra_forbidden` for a field we do not accept, `missing` for a required one, or `less_than_equal` for a number out of range. Switch on this rather than on `message`, which may be reworded. securitySchemes: bearerAuth: type: http scheme: bearer description: 'Your API key as a Bearer token, e.g. `Authorization: Bearer vk_…`.' ````