Hyperbolic

Hyperbolic Audio Generation API

Convert text to natural-sounding speech using Melo TTS (sunset) and Whisper (coming soon). POST /v1/audio/generation accepts text and speed; returns base64-encoded audio. Pricing from $0.001 per 1000 characters.

Hyperbolic Audio Generation API is one of 6 APIs that Hyperbolic publishes on the APIs.io network, described by a machine-readable OpenAPI specification.

This API exposes 1 machine-runnable capability that can be deployed as REST, MCP, or Agent Skill surfaces via Naftiko.

Tagged areas include AI, Audio, Inference, and Text To Speech. The published artifact set on APIs.io includes API documentation, an OpenAPI specification, and 1 Naftiko capability spec.

GitHub OpenAPI

Documentation

📖
Documentation
https://docs.hyperbolic.ai/inference/overview

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/hyperbolic-ai/refs/heads/main/openapi/hyperbolic-audio-generation-api-openapi.yml

Other Resources

🔗
NaftikoCapability
https://raw.githubusercontent.com/api-evangelist/hyperbolic-ai/refs/heads/main/capabilities/inference-audio-generation.yaml

OpenAPI Specification

hyperbolic-audio-generation-api-openapi.yml Raw ↑ 
openapi: 3.1.0
info:
  title: Hyperbolic Audio Generation API
  description: >
    Convert text to natural-sounding speech using audio models hosted by
    Hyperbolic — Melo TTS (sunset) and Whisper (coming soon). Returns
    base64-encoded audio. Pricing from $0.001 per 1000 characters.
  version: v1
  contact:
    name: Hyperbolic Support
    email: [email protected]
    url: https://docs.hyperbolic.ai
  license:
    name: Hyperbolic Terms of Use
    url: https://www.hyperbolic.ai/terms-of-use

servers:
  - url: https://api.hyperbolic.xyz/v1
    description: Hyperbolic Production Inference Server

security:
  - BearerAuth: []

tags:
  - name: Audio Generation
    description: Text-to-speech audio endpoint

paths:
  /audio/generation:
    post:
      summary: Hyperbolic Generate Audio
      description: >
        Generate speech audio from text using the selected TTS model.
      operationId: generateAudio
      tags:
        - Audio Generation
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AudioGenerationRequest'
            examples:
              BasicTTS:
                summary: Basic TTS request
                value:
                  text: Hello and welcome to Hyperbolic.
                  speed: 1.0
                  language: EN
      responses:
        '200':
          description: Successful audio generation
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AudioGenerationResponse'
        '400':
          description: Bad Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '429':
          description: Too Many Requests
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'

components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key

  schemas:
    AudioGenerationRequest:
      type: object
      required:
        - text
      properties:
        text:
          type: string
          description: Input text to convert to speech.
        speed:
          type: number
          minimum: 0.5
          maximum: 2.0
          default: 1.0
        language:
          type: string
          description: Language code (e.g. EN, ES, FR, JA, ZH, KR).
          default: EN
        voice:
          type: string
          description: Speaker / voice ID for the selected model.

    AudioGenerationResponse:
      type: object
      properties:
        audio:
          type: string
          description: Base64-encoded audio bytes (typically WAV or MP3).
        duration:
          type: number
          description: Audio length in seconds.

    ErrorResponse:
      type: object
      properties:
        error:
          type: object
          properties:
            message:
              type: string
            type:
              type: string
            code:
              type: string