Allmodels Oai API

openapi: 3.2.0
info:
  title: Allmodels Oai API
  version: '2026-10-15'
  description: 'GENERATED FROM DOCUMENTATION by API Evangelist on 2026-10-15: 11 operation(s) read from 14 public documentation page(s) (each operation names its page in x-source). This is not the provider''s published contract; Allmodels has published no machine-readable contract that the pipeline could find. Engine: local.'
  x-evidence-tiers:
    code-example: 14
    documentation: -3
    pages-with-code: 12
    pages-read: 14
  x-generated-from: documentation
  x-provenance: generated
  x-authored-by: API Evangelist
  x-generated: '2026-10-15'
  x-generator: generate-contract-from-docs.py
  x-engine: local
  x-sources:
  - https://allmodels.io/docs/api-reference/models/listModels
  - https://allmodels.io/docs/api-reference/voices/listVoices
  - https://allmodels.io/docs/api-reference/health/healthCheck
  - https://allmodels.io/docs/api-reference/openai-sdk/openAiSpeech
  - https://allmodels.io/docs/api-reference/providers/listProviders
  - https://allmodels.io/docs/api-reference/realtime/realtimeConnect
  - https://allmodels.io/docs/api-reference/voices/createCustomVoice
  - https://allmodels.io/docs/api-reference/native-tts/stt/nativeSttStream
  - https://allmodels.io/docs/api-reference/native-tts/stt/nativeTtsStream
  - https://allmodels.io/docs/api-reference/elevenlabs-sdk/speechEngineConversation
  - https://allmodels.io/docs
  - https://allmodels.io/docs/errors
  - https://allmodels.io/docs/authentication
  - https://allmodels.io/docs/speech-to-text
servers:
- url: https://api.allmodels.io
security:
- bearer: []
tags:
- name: Oai
paths:
  /oai/audio/{audioid}:
    get:
      operationId: get_oai_audio_audioid
      tags:
      - Oai
      summary: GET /oai/audio/speech
      x-source: https://allmodels.io/docs
      parameters:
      - name: audioid
        in: path
        required: true
        schema:
          type: string
      responses:
        '200':
          description: Success (status as documented)
      x-evidence:
        kind: code-example
        language: curl
        snippet: 'curl import { writeFile } from "node:fs/promises"; const response = await fetch("https://api.allmodels.io/oai/audio/speech", { method: "POST", headers: { Authorization: `Bearer ${process.env.ALLMODELS_API_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "elevenlabs/eleven_flash_v2_5", "voice": "21m00Tcm4TlvDq8ikWAM", "input": "Hello from AllModels", "response_format": '
        collapsed_from: 2 example path(s) differing only at audioId
    post:
      operationId: post_oai_audio_audioid
      tags:
      - Oai
      summary: POST /oai/audio/{audioid}
      description: Generates speech with the official OpenAI SDK. Set the client's base URL to https://api.allmodels.io/oai and use your AllModels API key.
      x-source: https://allmodels.io/docs/api-reference/openai-sdk/openAiSpeech
      parameters:
      - name: audioid
        in: path
        required: true
        schema:
          type: string
      - name: provider_order
        in: query
        required: false
        schema:
          type: array
        description: Comma-separated or repeated provider IDs in preferred order.
      - name: provider_only
        in: query
        required: false
        schema:
          type: array
        description: Comma-separated or repeated provider IDs. Only these providers may serve the request.
      - name: provider_ignore
        in: query
        required: false
        schema:
          type: array
        description: Comma-separated or repeated provider IDs that must not serve the request.
      - name: allow_fallbacks
        in: query
        required: false
        schema:
          type: boolean
        description: Set to false to prevent fallback to another provider.
      - name: provider_options
        in: query
        required: false
        schema:
          type: object
        description: Provider-specific options in bracket notation, such as provider_options[encoding]=linear16.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostOaiAudioAudioidRequest'
      responses:
        '200':
          description: Success (status as documented)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PostOaiAudioAudioidResponse'
      x-evidence:
        kind: documentation
        collapsed_from: 2 example path(s) differing only at audioId
components:
  schemas:
    PostOaiAudioAudioidRequest:
      type: object
      properties:
        model:
          type: string
          description: Model identifier, optionally provider-prefixed.
        voice:
          type: string
          description: Voice identifier.
        input:
          type: string
          description: Text to synthesize.
        response_format:
          type: string
          description: Desired audio format, e.g., mp3.
        stream_format:
          type: string
          description: Use "audio" for audio bytes or "sse" for OpenAI speech events.
      required:
      - model
      - voice
      - input
    PostOaiAudioAudioidResponse:
      type: object
      properties:
        '200':
          type: string
          description: Audio bytes of the generated speech.
        '400':
          type: string
          description: Error response.
        '401':
          type: string
          description: Error response.
        '402':
          type: string
          description: Error response.
        '403':
          type: string
          description: Error response.
        '422':
          type: string
          description: Error response.
        '502':
          type: string
          description: Error response.
  securitySchemes:
    bearer:
      type: http
      scheme: bearer