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.

Collections

Speech-to-speech (EVI)

OPEN

Expression Measurement API

OPEN

Text-to-Speech (TTS)

OPEN

Voices

OPEN

Pricing Plans

Hume Ai Plans Pricing

8 plans

PLANS

Rate Limits

Hume Ai Rate Limits

5 limits

RATE LIMITS

FinOps

Hume Ai Finops

FINOPS

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

opencollection: 1.0.0
info:
  name: Voices
  version: 1.0.0
items:
- info:
    name: subpackage_voices
    type: folder
  items:
  - info:
      name: List voices
      type: http
    http:
      method: GET
      url: https://api.hume.ai/v0/tts/voices
      headers:
      - name: X-Hume-Api-Key
        value: ''
      params:
      - name: provider
        value: ''
        type: query
        description: 'Specify the voice provider to filter voices returned by the endpoint:


          - **`HUME_AI`**: Lists preset, shared voices from Hume''s [Voice Library](https://app.hume.ai/tts/voice-library).

          - **`CUSTOM_VOICE`**: Lists custom voices created and saved to your account.'
      - name: page_number
        value: ''
        type: query
        description: 'Specifies the page number to retrieve, enabling pagination.


          This parameter uses zero-based indexing. For example, setting `page_number` to 0 retrieves the first page of results
          (items 0-9 if `page_size` is 10), setting `page_number` to 1 retrieves the second page (items 10-19), and so on.
          Defaults to 0, which retrieves the first page.'
      - name: page_size
        value: ''
        type: query
        description: 'Specifies the maximum number of results to include per page, enabling pagination. The value must be
          between 1 and 100, inclusive.


          For example, if `page_size` is set to 10, each page will include up to 10 items. Defaults to 10.'
      - name: ascending_order
        value: ''
        type: query
      - name: filter_tag
        value: ''
        type: query
        description: 'Filter voices by tag using `TAG:TAG_VALUE` syntax.


          For example, `GENDER:Male` returns only voices with the `GENDER` tag set to `Male`. Tag types are case-insensitive;
          tag values are case-sensitive.


          Multiple values are ANDed together; for example, `[GENDER:Male, LANGUAGE:Japanese]` returns only voices matching
          both criteria.'
    docs: Lists voices you have saved in your account, or voices from the [Voice Library](https://app.hume.ai/tts/voice-library).
  - info:
      name: Create voice
      type: http
    http:
      method: POST
      url: https://api.hume.ai/v0/tts/voices
      headers:
      - name: X-Hume-Api-Key
        value: ''
      body:
        type: json
        data: '{}'
    docs: 'Saves a new custom voice to your account using the specified TTS generation ID.


      Once saved, this voice can be reused in subsequent TTS requests, ensuring consistent speech style and prosody. For more
      details on voice creation, see the [Voices Guide](/docs/text-to-speech-tts/voices).'
  - info:
      name: Delete voice
      type: http
    http:
      method: DELETE
      url: https://api.hume.ai/v0/tts/voices
      headers:
      - name: X-Hume-Api-Key
        value: ''
      params:
      - name: name
        value: ''
        type: query
        description: Name of the voice to delete
    docs: Deletes a previously generated custom voice.
bundled: true