Neuphonic website screenshot

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.

4 APIs 0 Features
Text-to-SpeechVoice AIAudioStreamingWebSocketVoice CloningConversational AIReal-TimeMultilingualOn-Device AI

APIs

Neuphonic TTS SSE API

Server-Sent Events endpoint for real-time text-to-speech synthesis. Accepts POST requests with text content and returns streaming audio in PCM format. Supports language selectio...

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...

Pricing Plans

Neuphonic Plans Pricing

3 plans

PLANS

Rate Limits

Neuphonic Rate Limits

4 limits

RATE LIMITS

FinOps

Semantic Vocabularies

Neuphonic Context

5 classes · 29 properties

JSON-LD

Example Payloads

Clone Voice

5 fields

EXAMPLE

Create Agent

4 fields

EXAMPLE

List Voices

4 fields

EXAMPLE

Sse Speak

4 fields

EXAMPLE

Resources

🔗
Website
Website
🔗
Documentation
Documentation
👥
GitHubOrganization
GitHubOrganization
🔗
LinkedIn
LinkedIn
🔗
X
X
🟢
StatusPage
StatusPage
🔗
Playground
Playground
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps
🔗
Vocabulary
Vocabulary
🔗
JSONLDContext
JSONLDContext

Sources

Raw ↑
aid: neuphonic
name: Neuphonic
type: Index
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
url: https://raw.githubusercontent.com/api-evangelist/neuphonic/refs/heads/main/apis.yml
created: 2026-06-12
modified: 2026-06-12
specificationVersion: '0.19'
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 SSE API
  description: 'Server-Sent Events endpoint for real-time text-to-speech synthesis. Accepts POST requests with text content
    and returns streaming audio in PCM format. Supports language selection, voice selection, speed control, and sampling rate
    configuration.

    '
  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: https://api.neuphonic.com
  tags:
  - Text-to-Speech
  - SSE
  - Streaming
  - Audio
  properties:
  - type: Documentation
    url: https://docs.neuphonic.com/build-group/text-to-speech
  - type: OpenAPI
    url: https://docs.neuphonic.com/api-reference/tts/sse
  - type: OpenAPI
    url: openapi/neuphonic-openapi.yml
- 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
  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/
common:
- 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