Neuphonic

Neuphonic is an ultra-low-latency voice AI platform specializing in real-time text-to-speech synthesis with sub-25ms latency, making it suitable for conversational AI and live applications. The platform provides both a cloud-hosted API with WebSocket streaming and Server-Sent Events (SSE), as well as open-source on-device models (NeuTTS Air, NeuTTS Nano) that run without a GPU. Neuphonic supports nine languages including English, Spanish, German, French, Urdu, Japanese, Korean, Chinese, and Portuguese, and offers instant voice cloning from short audio samples. Developers can also build conversational AI agents via the Agent API, which integrates with GPT-4o and supports Model Context Protocol (MCP) servers. Authentication uses API keys passed via the X-API-KEY header for SSE and as a query parameter for WebSocket connections.

Neuphonic publishes 5 APIs on the APIs.io network, including TTS WebSocket API, Agents API, Ping API, and 2 more. Tagged areas include Text-to-Speech, Voice AI, Audio, Streaming, and WebSocket.

The Neuphonic catalog on APIs.io includes 1 JSON-LD context and 1 Spectral governance ruleset.

Neuphonic’s developer surface includes authentication, documentation, and 13 more developer resources.

🌐 Visit website 📡 Source on GitHub

46.6/100 developing ▬ flat Agent 24/100 agent aware saas Full breakdown ↓
scored 2026-09-08 · rubric v0.20.0

AccessFreemiumSelf serve⚡ Free to try

1 APIs

Text-to-Speech Voice AI Audio Streaming WebSocket Voice Cloning Conversational AI Real-Time Multilingual On-Device AI

Kin Score

Kin Score How this is scored →
scored 2026-09-08 · rubric v0.20.0

Composite quality — 46.6/100 · developing

Contract Quality 16.2 / 23

Developer Ergonomics 4.5 / 18

Access Clarity 7.1 / 18

Operational Transparency 5.9 / 12

Contract Governance 2.7 / 11

Discoverability 6.2 / 9

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 24/100 · agent aware

Machine-Readable Contract 18 / 18

Agentic Access Contract 10 / 10

Documented Reversibility 0 / 6

MCP Server 0 / 12

Machine-Readable Auth 10 / 10

Idempotency 0 / 9

Stable Error Semantics 0 / 8

Request/Response Examples 0 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 6 / 6

Agent Skills 0 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it carries 10 points of the composite. It is scored from the published contracts themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in front of it, and the first time that check is skipped a duplicate record is created. Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet, not penalised by it.

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/neuphonic: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 7

Individual APIs this provider publishes, each with its own machine-readable definition.

Neuphonic TTS WebSocket API

WebSocket endpoint for continuous, low-latency text-to-speech streaming. Enables real-time voice synthesis with sub-25ms latency, supporting multiple text chunks over a single p...

Neuphonic Voice Cloning API

REST API for creating and managing cloned voices. Accepts audio samples (MP3 or WAV, minimum 6 seconds, under 10MB) and generates a custom voice model. Supports creating, retrie...

Neuphonic Agent API

REST API for creating and managing conversational AI voice agents. Agents combine Neuphonic TTS with GPT-4o for interactive voice applications and support Model Context Protocol...

Neuphonic Agents API

The Agents API from Neuphonic — 3 operation(s) for agents.

Neuphonic Ping API

The Ping API from Neuphonic — 1 operation(s) for ping.

Neuphonic Sse API

The Sse API from Neuphonic — 2 operation(s) for sse.

Neuphonic Voices API

The Voices API from Neuphonic — 2 operation(s) for voices.

Scroll for all 7

Open Collections 5

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Neuphonic Agents API

OPEN COLLECTION

Neuphonic Agents Ping API

OPEN COLLECTION

Neuphonic Agents Sse API

OPEN COLLECTION

Neuphonic Agents Voices API

OPEN COLLECTION

Pricing Plans 1

Published pricing tiers and plan structures.

Neuphonic Plans Pricing

3 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Neuphonic Rate Limits

4 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Neuphonic Finops

FINOPS

Semantic Vocabularies 1

JSON-LD contexts and semantic vocabularies used across these APIs.

Neuphonic Context

5 classes · 29 properties

JSON-LD

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Neuphonic API Rules

5 rules · 4 warnings 1 info

SPECTRAL

JSON Schema 3

Standalone JSON Schema definitions for this provider's data models.

Agent

7 properties

JSON SCHEMA

SSE TTS Request

4 properties

JSON SCHEMA

Voice

5 properties

JSON SCHEMA

Examples 4

Example request and response payloads for these APIs.

Clone Voice

5 fields

EXAMPLE

Create Agent

4 fields

EXAMPLE

List Voices

4 fields

EXAMPLE

Sse Speak

4 fields

EXAMPLE

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Neuphonic Authentication

apiKey · 2 schemes

SECURITY

Neuphonic Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Neuphonic Agentic Access

12 operations · 8 acting

AGENTIC

Resources

Documentation 1

Reference material describing how the API behaves

Documentation

Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess

AgenticAccess

Design & Contract 2

Pagination, idempotency, versioning, errors, and events

Vocabulary

Vocabulary

JSONLDContext

JSONLDContext

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 2

Status, limits, changes, and where to get help

StatusPage

StatusPage

RateLimits

RateLimits

Commercial 2

Pricing, plans, and the legal terms of use

Plans

Plans

FinOps

FinOps

Company 2

The organization behind the API

Website

Website

LinkedIn

Other 2

Properties that don't map to a standard resource type

Playground

Playground

Source (apis.yml)

aid: neuphonic
name: Neuphonic
type: Index
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Freemium · Self-serve signup
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-09-03'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/neuphonic.png
url: https://raw.githubusercontent.com/api-evangelist/neuphonic/refs/heads/main/apis.yml
created: 2026-06-12
modified: 2026-06-12
specificationVersion: '0.23'
description: 'Neuphonic is an ultra-low-latency voice AI platform specializing in real-time text-to-speech synthesis with
  sub-25ms latency, making it suitable for conversational AI and live applications. The platform provides both a cloud-hosted
  API with WebSocket streaming and Server-Sent Events (SSE), as well as open-source on-device models (NeuTTS Air, NeuTTS Nano)
  that run without a GPU. Neuphonic supports nine languages including English, Spanish, German, French, Urdu, Japanese, Korean,
  Chinese, and Portuguese, and offers instant voice cloning from short audio samples. Developers can also build conversational
  AI agents via the Agent API, which integrates with GPT-4o and supports Model Context Protocol (MCP) servers. Authentication
  uses API keys passed via the X-API-KEY header for SSE and as a query parameter for WebSocket connections.

  '
tags:
- Text-to-Speech
- Voice AI
- Audio
- Streaming
- WebSocket
- Voice Cloning
- Conversational AI
- Real-Time
- Multilingual
- On-Device AI
apis:
- name: Neuphonic TTS WebSocket API
  description: 'WebSocket endpoint for continuous, low-latency text-to-speech streaming. Enables real-time voice synthesis
    with sub-25ms latency, supporting multiple text chunks over a single persistent connection. Includes a 60-second connection
    timeout and requires a STOP token to signal completion.

    '
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.neuphonic.com/build-group/text-to-speech
  baseURL: wss://api.neuphonic.com
  tags:
  - Text-to-Speech
  - WebSocket
  - Real-Time
  - Streaming
  properties:
  - type: Documentation
    url: https://docs.neuphonic.com/build-group/text-to-speech
  - type: AsyncAPI
    url: https://docs.neuphonic.com/api-reference/tts/websocket
- name: Neuphonic Voice Cloning API
  description: 'REST API for creating and managing cloned voices. Accepts audio samples (MP3 or WAV, minimum 6 seconds, under
    10MB) and generates a custom voice model. Supports creating, retrieving, updating, listing, and deleting cloned voices.
    Voice cloning is available in English, French, German, and Spanish.

    '
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.neuphonic.com/build-group/voice-cloning
  baseURL: https://api.neuphonic.com
  tags:
  - Voice Cloning
  - Audio
  - Machine-Learning
  tags_raw:
  - Voice Cloning
  - Audio
  - Machine Learning
  properties:
  - type: Documentation
    url: https://docs.neuphonic.com/build-group/voice-cloning
- name: Neuphonic Agent API
  description: 'REST API for creating and managing conversational AI voice agents. Agents combine Neuphonic TTS with GPT-4o
    for interactive voice applications and support Model Context Protocol (MCP) server integration, multilingual operation,
    and interruption handling for natural conversational flow.

    '
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.neuphonic.com/
  baseURL: https://api.neuphonic.com
  tags:
  - Agents
  - Conversational AI
  - Voice Assistant
  properties:
  - type: Documentation
    url: https://docs.neuphonic.com/
- aid: neuphonic:neuphonic-agents-api
  name: Neuphonic Agents API
  description: The Agents API from Neuphonic — 3 operation(s) for agents.
  humanURL: https://docs.neuphonic.com/build-group/text-to-speech
  baseURL: https://api.neuphonic.com
  tags:
  - Agents
  properties:
  - type: OpenAPI
    url: openapi/neuphonic-agents-api-openapi.yml
  - type: Documentation
    url: https://docs.neuphonic.com/build-group/text-to-speech
- aid: neuphonic:neuphonic-ping-api
  name: Neuphonic Ping API
  description: The Ping API from Neuphonic — 1 operation(s) for ping.
  humanURL: https://docs.neuphonic.com/build-group/text-to-speech
  baseURL: https://api.neuphonic.com
  tags:
  - Ping
  properties:
  - type: OpenAPI
    url: openapi/neuphonic-ping-api-openapi.yml
  - type: Documentation
    url: https://docs.neuphonic.com/build-group/text-to-speech
- aid: neuphonic:neuphonic-sse-api
  name: Neuphonic Sse API
  description: The Sse API from Neuphonic — 2 operation(s) for sse.
  humanURL: https://docs.neuphonic.com/build-group/text-to-speech
  baseURL: https://api.neuphonic.com
  tags:
  - SSE
  tags_raw:
  - Sse
  properties:
  - type: OpenAPI
    url: openapi/neuphonic-sse-api-openapi.yml
  - type: Documentation
    url: https://docs.neuphonic.com/build-group/text-to-speech
- aid: neuphonic:neuphonic-voices-api
  name: Neuphonic Voices API
  description: The Voices API from Neuphonic — 2 operation(s) for voices.
  humanURL: https://docs.neuphonic.com/build-group/text-to-speech
  baseURL: https://api.neuphonic.com
  tags:
  - Voices
  properties:
  - type: OpenAPI
    url: openapi/neuphonic-voices-api-openapi.yml
  - type: Documentation
    url: https://docs.neuphonic.com/build-group/text-to-speech
common:
- type: AgenticAccess
  url: agentic-access/neuphonic-agentic-access.yml
- type: DomainSecurity
  url: security/neuphonic-domain-security.yml
- type: Authentication
  url: authentication/neuphonic-authentication.yml
- type: Website
  url: https://www.neuphonic.com/
- type: Documentation
  url: https://docs.neuphonic.com/
- type: GitHubOrganization
  url: https://github.com/neuphonic
- type: LinkedIn
  url: https://uk.linkedin.com/company/neuphonic
- type: X
  url: https://twitter.com/neuphonicspeech
- type: StatusPage
  url: https://status.neuphonic.com/
- type: Playground
  url: https://app.neuphonic.com/
- type: Plans
  url: plans/neuphonic-plans-pricing.yml
- type: RateLimits
  url: rate-limits/neuphonic-rate-limits.yml
- type: FinOps
  url: finops/neuphonic-finops.yml
- type: Vocabulary
  url: vocabulary/neuphonic-vocabulary.yml
- type: JSONLDContext
  url: json-ld/neuphonic-context.jsonld
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com

Work with this as data

Every provider 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 providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
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 provider

curl "https://apis.io/api/v1/providers/neuphonic"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/neuphonic/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/neuphonic/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

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.

GitHub Google LinkedIn

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