Ditto Audio Inference API

The pure text+model→audio inference service — stateless, no book/persistence awareness

Operations 6

GET /v1/inference/quota Your current entitlements (parallel limit, voices) #
POST /v1/inference/start Start a cloud inference session (enforces tier parallel limit) #
GET /v1/inference/sessions List your own inference sessions (pre-render/convert jobs) #
GET /v1/inference/{id} Poll a session/job — status + progress (chunksRendered/totalChunks) #
POST /v1/inference/{id}/heartbeat Keep a session alive (call every ~20s while active) #
POST /v1/inference/{id}/end End a session #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/ditto-audio:ditto-audio-inference-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

ditto-audio-inference-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: ditto.audio Inference API
  description: Cloud API behind ditto.audio. The reader (reader.ditto.audio) and the voice studio (studio.ditto.audio) are separate apps sharing this one backend — see /docs/reader and /docs/inference for each app’s public surface. Third-party integrations want /docs/public (rendered for humans at https://ditto.audio/docs).
  version: '1.0'
  contact: {}
servers: []
tags:
- name: Inference
  description: The pure text+model→audio inference service — stateless, no book/persistence awareness
paths:
  /v1/inference/quota:
    get:
      operationId: InferenceController_quota
      parameters: []
      responses:
        '200':
          description: ''
      security:
      - bearer: []
      summary: Your current entitlements (parallel limit, voices)
      tags:
      - Inference
  /v1/inference/start:
    post:
      operationId: InferenceController_start
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/StartDto'
      responses:
        '201':
          description: ''
      security:
      - bearer: []
      summary: Start a cloud inference session (enforces tier parallel limit)
      tags:
      - Inference
  /v1/inference/sessions:
    get:
      operationId: InferenceController_sessions
      parameters: []
      responses:
        '200':
          description: ''
      security:
      - bearer: []
      summary: List your own inference sessions (pre-render/convert jobs)
      tags:
      - Inference
  /v1/inference/{id}:
    get:
      operationId: InferenceController_get
      parameters:
      - name: id
        required: true
        in: path
        schema:
          type: string
      responses:
        '200':
          description: ''
      security:
      - bearer: []
      summary: Poll a session/job — status + progress (chunksRendered/totalChunks)
      tags:
      - Inference
  /v1/inference/{id}/heartbeat:
    post:
      operationId: InferenceController_heartbeat
      parameters:
      - name: id
        required: true
        in: path
        schema:
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/InferenceHeartbeatDto'
      responses:
        '201':
          description: ''
      security:
      - bearer: []
      summary: Keep a session alive (call every ~20s while active)
      tags:
      - Inference
  /v1/inference/{id}/end:
    post:
      operationId: InferenceController_end
      parameters:
      - name: id
        required: true
        in: path
        schema:
          type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EndDto'
      responses:
        '201':
          description: ''
      security:
      - bearer: []
      summary: End a session
      tags:
      - Inference
components:
  schemas:
    InferenceHeartbeatDto:
      type: object
      properties: {}
    StartDto:
      type: object
      properties: {}
    EndDto:
      type: object
      properties: {}
  securitySchemes:
    bearer:
      scheme: bearer
      bearerFormat: ditto_sk_live_… API key, ditto_oat_… OAuth access token, or a session JWT
      type: http
      description: An API key (`ditto_sk_live_…`, made at https://ditto.audio/account/api-keys) authenticates /v1/audio/* and /v1/reader/*; an OAuth connection's one-hour access token (`ditto_oat_…`) holds the audio:read and audio:speech scopes only. Account routes (/v1/api-keys, /v1/usage, /v1/subscription) take the signed-in session's token (a JWT) only.