Hume AI

Hume AI builds empathic voice and emotional AI models. The platform exposes four published APIs: Voices, Octave Text-to-Speech, Empathic Voice Interface (EVI / speech-to-speech), and Expression Measurement (multimodal emotion analysis). REST + WebSocket interfaces are documented with public OpenAPI and AsyncAPI specifications at https://dev.hume.ai/.

4 APIs 0 Features

AIVoiceEmpathicEmotionMultimodal

APIs

Hume Voices API

REST API for managing custom voices used by Hume's TTS and EVI products. Supports voice creation, listing, and deletion. Bearer token auth.

Hume Octave Text-to-Speech API

REST API for synthesizing expressive speech using Octave. Supports streamed JSON/file and standard JSON/file responses, plus voice conversion endpoints.

Hume Empathic Voice Interface (EVI) API

Real-time emotionally intelligent speech-to-speech voice interface delivered over WebSockets. Includes configuration, prompt, and tool management plus chat history, chat group o...

Hume Expression Measurement API

Multimodal emotion analysis API for face, voice, language, and burst expression. Offers batch inference jobs over images/audio/video/text, and streaming inference.

Event Specifications

Hume AI WebSocket APIs

Consolidated AsyncAPI definition for Hume AI's two production WebSocket surfaces: - **Empathic Voice Interface (EVI)** — bidirectional speech-to-speech voice conversation at `ws...

ASYNCAPI

Resources

👥

GitHubOrganization

Sources

aid: hume-ai
url: https://raw.githubusercontent.com/api-evangelist/hume-ai/refs/heads/main/apis.yml
name: Hume AI
kind: company
description: >-
  Hume AI builds empathic voice and emotional AI models. The platform exposes four published APIs: Voices, Octave
  Text-to-Speech, Empathic Voice Interface (EVI / speech-to-speech), and Expression Measurement (multimodal emotion
  analysis). REST + WebSocket interfaces are documented with public OpenAPI and AsyncAPI specifications at
  https://dev.hume.ai/.
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
tags:
  - AI
  - Voice
  - Empathic
  - Emotion
  - Multimodal
created: '2026-05-08'
modified: '2026-05-29'
specificationVersion: '0.19'
apis:
  - aid: hume-ai:voices
    name: Hume Voices API
    description: >-
      REST API for managing custom voices used by Hume's TTS and EVI products. Supports voice creation, listing, and
      deletion. Bearer token auth.
    image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
    humanURL: https://dev.hume.ai/reference
    baseURL: https://api.hume.ai
    tags:
      - Voices
      - Voice Cloning
      - TTS
    properties:
      - type: Documentation
        url: https://dev.hume.ai/reference
      - type: OpenAPI
        url: openapi/hume-ai-voices-openapi.yml
  - aid: hume-ai:tts
    name: Hume Octave Text-to-Speech API
    description: >-
      REST API for synthesizing expressive speech using Octave. Supports streamed JSON/file and standard JSON/file
      responses, plus voice conversion endpoints.
    image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
    humanURL: https://dev.hume.ai/docs/text-to-speech-tts
    baseURL: https://api.hume.ai
    tags:
      - TTS
      - Speech Synthesis
      - Streaming
      - Octave
    properties:
      - type: Documentation
        url: https://dev.hume.ai/docs/text-to-speech-tts
      - type: OpenAPI
        url: openapi/hume-ai-tts-openapi.yml
      - type: Pricing
        url: https://www.hume.ai/pricing
  - aid: hume-ai:evi
    name: Hume Empathic Voice Interface (EVI) API
    description: >-
      Real-time emotionally intelligent speech-to-speech voice interface delivered over WebSockets. Includes
      configuration, prompt, and tool management plus chat history, chat group operations, and webhook events for tool
      calls and chat lifecycle.
    image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
    humanURL: https://dev.hume.ai/docs/speech-to-speech-evi
    baseURL: https://api.hume.ai
    tags:
      - EVI
      - Speech-to-Speech
      - WebSocket
      - Realtime
      - Empathic
    properties:
      - type: Documentation
        url: https://dev.hume.ai/docs/speech-to-speech-evi
      - type: OpenAPI
        url: openapi/hume-ai-evi-openapi.yml
      - type: AsyncAPI
        url: https://dev.hume.ai/asyncapi.yaml
      - type: AsyncAPI
        url: asyncapi/hume-ai-asyncapi.yml
  - aid: hume-ai:expression
    name: Hume Expression Measurement API
    description: >-
      Multimodal emotion analysis API for face, voice, language, and burst expression. Offers batch inference jobs over
      images/audio/video/text, and streaming inference.
    image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
    humanURL: https://dev.hume.ai/docs/expression-measurement
    baseURL: https://api.hume.ai
    tags:
      - Expression Measurement
      - Emotion
      - Multimodal
      - Batch
      - Streaming
    properties:
      - type: Documentation
        url: https://dev.hume.ai/docs/expression-measurement
      - type: OpenAPI
        url: openapi/hume-ai-expression-openapi.yml
      - type: AsyncAPI
        url: asyncapi/hume-ai-asyncapi.yml
common:
  - type: GitHubOrganization
    url: https://github.com/HumeAI
  - type: LinkedIn
    url: https://www.linkedin.com/company/hume-ai
  - type: Website
    url: https://www.hume.ai/
  - type: Documentation
    url: https://dev.hume.ai/
  - type: Plans
    url: plans/hume-ai-plans-pricing.yml
  - type: RateLimits
    url: rate-limits/hume-ai-rate-limits.yml
  - type: FinOps
    url: finops/hume-ai-finops.yml
maintainers:
  - FN: Kin Lane
    email: kin@apievangelist.com