> ## Documentation Index
> Fetch the complete documentation index at: https://docs.teamfollowup.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use the public API base URL: https://api.teamfollowup.ai/api.
> Authenticate public API requests with Authorization: Bearer YOUR_API_KEY.
> Use product-owned terms: agents, campaigns, projects (GoHighLevel sub-accounts), contacts, calls, outcomes, skills, cadences, phone numbers.
> Scope requests by locationId rather than projectName.
> Read the guide linked from each API reference group before recommending an endpoint.

# Add a voice

> Add a voice to this agency's library so its agents can speak with it. Find the id with `POST /voices/search`. The voice is copied into every library the agency's agents are served from and still counts once against the allowance. Returns the whole library, so no follow-up read is needed.

A voice already on the account (another agency added it, or this agency added and later removed it) is not added again: the request answers 409 `VOICE_ALREADY_SHARED`, spends nothing, and `references.voiceId` names the voice to select instead. It is already in `GET /voices` with `source: "shared"`.

Required API key scope: `voices:write`.



## OpenAPI

````yaml /openapi.yaml post /api/agent-builder/voices/library
openapi: 3.1.0
info:
  title: TFUAI Server API
  version: 1.0.0
  description: >-
    API reference for the TFUAI SaaS server.


    All published endpoints are mounted under `/api`. Responses use a standard
    envelope: `{ "success": true, ... }` on success and `{ "success": false,
    "error": "..." }` on failure.


    Product API modules are being launched module by module. This spec currently
    exposes only contracted public modules.


    Authenticate public API requests with an API key in the `Authorization`
    header: `Authorization: Bearer YOUR_API_KEY`.
servers:
  - url: https://api.teamfollowup.ai
    description: Production API origin. Public API paths are under /api.
security: []
tags:
  - name: Agents
    description: Manage voice agents, campaigns, workflows, and outcomes.
  - name: Analytics
    description: >-
      Minimal, non-billing performance summary: volume, conversion, and pickup
      metrics.
  - name: Billing
    description: >-
      Billing for your own agency: balance, spend, transaction history, invoices
      and sub-account wallets; auto-recharge, rebilling, Credit Guard and Stripe
      customers; and, with the billing:charge scope, purchases and charges.
  - name: Calls
    description: Review calls, test runs, and execution history.
  - name: Campaign Workflows
    description: >-
      What runs after a call lands: for each outcome (booked, opted out, asked
      for a callback…), an ordered chain of actions — tag the contact, move a
      pipeline stage, send an SMS, book an appointment. Stored as a graph:
      `nodes` are the actions, `edges` say what follows what, and
      `dispositionEntries` maps each outcome to the node its chain starts at.


      **Pick the narrowest endpoint that does the job.**


      | To | Call | |

      | --- | --- | --- |

      | See what fires per outcome | `GET .../workflow/digest` | Reads as plain
      text, no graph walking |

      | Add steps to an outcome | `POST .../outcomes/{outcome}/nodes` | Server
      derives node ids, edge ids, handles, layout |

      | Change a message, tag or setting | `PATCH .../workflow` | Merges;
      carries no graph, so it cannot damage one |

      | Remove one step | `DELETE .../nodes/{nodeId}` | Also re-links the chain
      around it |

      | Author or replace the whole graph | `PUT .../workflow` | Replaces
      everything you send |


      `PUT` is the only one that can re-wire, position nodes, build an `if`,
      save an unconfigured draft, or copy a whole workflow — and the only one
      that can overwrite a change someone else made after you read it. Use it
      when you are genuinely authoring the graph, and send `expectedVersion`
      when you do. For everything else the narrower endpoints are both easier
      and safer.
  - name: Contacts
    description: Contact list, filters, contact call history, and do-not-call actions.
  - name: GHL
    description: CRM variables and contact helpers used by agent and campaign setup flows.
  - name: Phone Numbers
    description: >-
      Caller ID pool, number search, assignment, movement, and release
      endpoints.
  - name: Power Dialer
    description: >-
      Power Dialer queue, lead cadence, callback, parked lead, and campaign
      schedule endpoints.
  - name: Projects
    description: >-
      Project management endpoints: list, update, disconnect, configure project
      campaigns, and validate setup.
  - name: Skills and Tools
    description: Manage reusable agent behaviors and in-call tool descriptions.
  - name: Split Testing
    description: >-
      Split live campaign traffic across agent variants and shift the weights
      between them.
  - name: Voices
    description: Voice catalogue endpoints for choosing the voice used by an agent.
paths:
  /api/agent-builder/voices/library:
    post:
      tags:
        - Voices
      summary: Add a voice
      description: >-
        Add a voice to this agency's library so its agents can speak with it.
        Find the id with `POST /voices/search`. The voice is copied into every
        library the agency's agents are served from and still counts once
        against the allowance. Returns the whole library, so no follow-up read
        is needed.


        A voice already on the account (another agency added it, or this agency
        added and later removed it) is not added again: the request answers 409
        `VOICE_ALREADY_SHARED`, spends nothing, and `references.voiceId` names
        the voice to select instead. It is already in `GET /voices` with
        `source: "shared"`.


        Required API key scope: `voices:write`.
      operationId: add-voice-to-library
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VoicesAddVoiceRequest'
            examples:
              default:
                value:
                  providerVoiceId: EXAVITQu4vr4xnSDxMaL
                  displayName: Sarah (warm)
      responses:
        '201':
          description: Voice added. The full library is returned.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesLibraryResponse'
              examples:
                default:
                  value:
                    success: true
                    voices:
                      - providerVoiceId: EXAVITQu4vr4xnSDxMaL
                        displayName: Sarah (warm)
                        addedAt: '2026-09-04T11:20:00.000Z'
                        voiceIds:
                          - custom_voice_9b1f2a7c4d3e5f6a8b0c1d2e3f
                    used: 1
                    limit: 5
                    remaining: 4
        '400':
          description: >-
            The request is malformed (`BadRequest`), or the library refused it
            (`VALIDATION`), for example because the voice is already in your
            library.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesErrorResponse'
              examples:
                validation:
                  value:
                    success: false
                    error: VALIDATION
                    message: That voice is already in your library.
                badRequest:
                  value:
                    success: false
                    error: BadRequest
                    message: voiceId required
        '401':
          description: Missing or invalid authentication.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesErrorResponse'
              examples:
                default:
                  value:
                    success: false
                    error: Unauthorized
                    message: Authentication required.
        '403':
          description: Authenticated but not permitted to use the voice endpoints.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesErrorResponse'
              examples:
                default:
                  value:
                    success: false
                    error: Forbidden
                    message: You do not have access to voice catalogue endpoints.
        '404':
          description: >-
            No voice with that `providerVoiceId` in the provider's public
            library.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesErrorResponse'
              examples:
                default:
                  value:
                    success: false
                    error: NOT_FOUND
                    message: We could not find that voice. Check the ID and try again.
        '409':
          description: >-
            The voice cannot be added as asked. `VOICE_ALLOWANCE`: the plan's
            voice allowance is used up; remove a voice or upgrade.
            `VOICE_CAPACITY`: new voices are temporarily unavailable; contact
            support. `VOICE_ALREADY_SHARED`: the voice is already on the
            account, so nothing was added or spent; select `references.voiceId`
            on the agent instead.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesErrorResponse'
              examples:
                allowance:
                  value:
                    success: false
                    error: VOICE_ALLOWANCE
                    message: >-
                      Your plan includes 5 custom voices. Remove one or upgrade
                      to add another.
                capacity:
                  value:
                    success: false
                    error: VOICE_CAPACITY
                    message: >-
                      New voices are temporarily unavailable. Contact support
                      and we will sort it out.
                alreadyShared:
                  value:
                    success: false
                    error: VOICE_ALREADY_SHARED
                    message: >-
                      That voice is already on your account. Pick it from the
                      shared list.
                    references:
                      voiceId: custom_voice_9b1f2a7c4d3e5f6a8b0c1d2e3f
        '429':
          description: Rate limit exceeded.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesErrorResponse'
              examples:
                default:
                  value:
                    success: false
                    error: TooManyRequests
                    message: Too many requests, please try again later.
        '500':
          description: Unexpected server error.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoicesErrorResponse'
              examples:
                default:
                  value:
                    success: false
                    error: InternalError
                    message: Unexpected server error.
      security:
        - ApiKeyAuth: []
      x-codeSamples:
        - lang: bash
          label: cURL
          source: |-
            curl --request POST \
              --url https://api.teamfollowup.ai/api/agent-builder/voices/library \
              --header 'Authorization: Bearer YOUR_API_KEY' \
              --header 'Content-Type: application/json' \
              --data '{
              "providerVoiceId": "EXAVITQu4vr4xnSDxMaL",
              "displayName": "Sarah (warm)"
            }'
components:
  schemas:
    VoicesAddVoiceRequest:
      type: object
      additionalProperties: false
      required:
        - providerVoiceId
      properties:
        providerVoiceId:
          type: string
          minLength: 1
          description: The provider voice id to add, as returned by the search.
          example: EXAVITQu4vr4xnSDxMaL
        displayName:
          type: string
          minLength: 1
          maxLength: 200
          description: >-
            What to call this voice in the picker. Defaults to the provider's
            own name.
          example: Sarah (warm)
    VoicesLibraryResponse:
      type: object
      additionalProperties: false
      required:
        - success
        - voices
        - used
        - limit
        - remaining
      properties:
        success:
          type: boolean
        voices:
          type: array
          items:
            $ref: '#/components/schemas/VoicesLibraryVoice'
        used:
          type: integer
          minimum: 0
          description: Voices currently added.
          example: 1
        limit:
          type:
            - integer
            - 'null'
          minimum: 0
          description: How many voices this account may add. Null means unlimited.
          example: 5
        remaining:
          type:
            - integer
            - 'null'
          minimum: 0
          description: >-
            Voices still addable. Null whenever `limit` is null: an unlimited
            allowance has no remainder, and reporting a number here would be
            inventing one.
          example: 4
    VoicesErrorResponse:
      type: object
      additionalProperties: {}
      required:
        - success
        - error
        - message
      properties:
        success:
          type: boolean
        error:
          type: string
          description: >-
            Machine-readable error code. The catalogue reads answer `BadRequest`
            and `NotFound`. The voice library answers `VALIDATION`, `NOT_FOUND`,
            `FORBIDDEN`, `VOICE_ALLOWANCE` (the plan's voice allowance is used
            up), `VOICE_CAPACITY` (new voices are temporarily unavailable) and
            `VOICE_ALREADY_SHARED` (the voice is already on the account; see
            `references`).
          example: NotFound
        message:
          type: string
          description: Human-readable explanation safe to show to an operator.
          example: Voice "custom_voice_missing" not found.
        references:
          type: object
          additionalProperties: false
          description: >-
            Sent only with `VOICE_ALREADY_SHARED`: what to use instead of
            adding.
          properties:
            voiceId:
              type: string
              description: >-
                The id of the voice already on the account. Select it on the
                agent rather than adding the voice again.
              example: custom_voice_9b1f2a7c4d3e5f6a8b0c1d2e3f
    VoicesLibraryVoice:
      type: object
      additionalProperties: false
      required:
        - providerVoiceId
        - displayName
        - addedAt
        - voiceIds
      description: One voice the agency added for itself.
      properties:
        providerVoiceId:
          type: string
          description: >-
            The voice id as the speech provider knows it. This is the id to send
            when removing the voice or asking what removing it would affect.
          example: EXAVITQu4vr4xnSDxMaL
        displayName:
          type:
            - string
            - 'null'
          description: >-
            What this voice is called in the picker. Null when the provider's
            own name is used.
          example: Sarah (warm)
        addedAt:
          type:
            - string
            - 'null'
          format: date-time
          example: '2026-09-04T11:20:00.000Z'
        voiceIds:
          type: array
          items:
            type: string
          description: >-
            The ids to select this voice on an agent. Plural because the voice
            is held in every library the agency's agents are served from, and
            only the copy in a given agent's library will play. It still counts
            as one voice against the allowance, however many copies it takes.
          example:
            - custom_voice_9b1f2a7c4d3e5f6a8b0c1d2e3f
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
      bearerFormat: API key
      description: 'Send your API key as `Authorization: Bearer YOUR_API_KEY`.'

````