Unisound

Unisound (云知声) is a Chinese AGI technology company delivering conversational AI across smart living and smart healthcare. Its Token Hub MaaS platform exposes OpenAI- and Anthropic-compatible APIs for the Unisound U2 agent-native large language model and U2-Med medical model, plus U2-ASR speech transcription, U2-TTS synthesis and voice cloning, voiceprint, and U1-OCR document parsing services, alongside the legacy AI Open Platform WebSocket speech APIs and the Shanhai (UniGPT) LLM WebAPI.

Unisound publishes 3 APIs on the APIs.io network. Tagged areas include Company, Artificial Intelligence, Speech Recognition, Text-to-Speech, and Voice Cloning.

Unisound’s developer surface includes documentation, API reference, getting-started guide, pricing, support, signup flow, changelog, and 19 more developer resources.

46.1/100 developing ▬ flat Agent 24/100 agent aware Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
3 APIs
CompanyArtificial IntelligenceSpeech RecognitionText-to-SpeechVoice CloningLarge Language ModelsOCRHealthcareMachine LearningVoice

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 46.1/100 · developing
Contract Quality 0.0 / 25
Developer Ergonomics 12.6 / 20
Commercial Clarity 15.3 / 20
Operational Transparency 6.8 / 13
Governance 0.0 / 12
Discoverability 10.0 / 10
Agent readiness — 24/100 · agent aware
Machine-Readable Contract 0 / 18
Agentic Access Contract 0 / 15
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 0 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/unisound: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 3

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

Unisound Token Hub API

Multi-modal MaaS API for Unisound U2 models: OpenAI-compatible chat completions and Anthropic-compatible messages for the U2 and U2-Med LLMs (streaming, function calling, struct...

Unisound Shanhai (UniGPT) LLM WebAPI

REST chat-completions WebAPI for the Shanhai (山海 / UniGPT) large language model on the Unisound AI Open Platform. POST rest/v1.1/chat/completions with signature-based authentica...

Unisound AI Open Platform Speech WebAPI

WebSocket speech APIs on the Unisound AI Open Platform: one-sentence speech recognition (Mandarin, Cantonese, Sichuanese, English; domain models for medical, finance, law, and m...

Pricing Plans 1

Published pricing tiers and plan structures.

Unisound Plans

3 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Unisound Rate Limits

9 limits

RATE LIMITS

Security Posture 2

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

Unisound Authentication

apiKey/signature · 3 schemes

SECURITY

Unisound Domain Security

TLSv1.3 · HSTS

SECURITY

Resources

Get Started 4

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Build 3

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 5

Status, limits, changes, and where to get help

Commercial 4

Pricing, plans, and the legal terms of use

Company 1

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
aid: unisound
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/unisound.png
name: Unisound
description: Unisound (云知声) is a Chinese AGI technology company delivering conversational AI across smart living and smart
  healthcare. Its Token Hub MaaS platform exposes OpenAI- and Anthropic-compatible APIs for the Unisound U2 agent-native large
  language model and U2-Med medical model, plus U2-ASR speech transcription, U2-TTS synthesis and voice cloning, voiceprint,
  and U1-OCR document parsing services, alongside the legacy AI Open Platform WebSocket speech APIs and the Shanhai (UniGPT)
  LLM WebAPI.
url: https://raw.githubusercontent.com/api-evangelist/unisound/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- qiming
x-tier: enriched
x-tier-reason: real-api-surface
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-21'
tags:
- Company
- Artificial Intelligence
- Speech Recognition
- Text-to-Speech
- Voice Cloning
- Large Language Models
- OCR
- Healthcare
- Machine Learning
- Voice
apis:
- name: Unisound Token Hub API
  description: 'Multi-modal MaaS API for Unisound U2 models: OpenAI-compatible chat completions and Anthropic-compatible messages
    for the U2 and U2-Med LLMs (streaming, function calling, structured output, context caching, prefix continuation), WebSocket
    one-shot and real-time speech recognition, asynchronous long-audio transcription and long-text speech synthesis via task
    polling, voiceprint registration and lookup, voice cloning and timbre management, asynchronous document parsing and information
    extraction (U1-OCR), and file management. Authenticated with Bearer API keys.'
  humanURL: https://maas.unisound.com/docs/api/overview
  baseURL: https://maas-api.unisound.com/v1
  tags:
  - LLM
  - Speech Recognition
  - Text-to-Speech
  - Voice Cloning
  - OCR
  properties:
  - type: Documentation
    url: https://maas.unisound.com/docs
  - type: APIReference
    url: https://maas.unisound.com/docs/api/overview
- name: Unisound Shanhai (UniGPT) LLM WebAPI
  description: REST chat-completions WebAPI for the Shanhai (山海 / UniGPT) large language model on the Unisound AI Open Platform.
    POST rest/v1.1/chat/completions with signature-based authentication (SHA-256 over appkey + udid + timestamp + secret),
    supporting streaming and non-streaming responses.
  humanURL: https://ai.unisound.com/doc/unigpt/WebAPI.html
  baseURL: https://unigpt-api.hivoice.cn
  tags:
  - LLM
  - Chat
- name: Unisound AI Open Platform Speech WebAPI
  description: 'WebSocket speech APIs on the Unisound AI Open Platform: one-sentence speech recognition (Mandarin, Cantonese,
    Sichuanese, English; domain models for medical, finance, law, and more), real-time transcription, audio file transcription,
    oral evaluation, voiceprint, and speech synthesis. Signature-based authentication (SHA-256 over appkey + timestamp + secret);
    iOS, Android, and HarmonyOS SDKs.'
  humanURL: https://ai.unisound.com/doc/asronesentence/WebAPI.html
  baseURL: wss://ws-osasr.hivoice.cn/v1/asr
  tags:
  - Speech Recognition
  - Text-to-Speech
  - Voice
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: DomainSecurity
  url: security/unisound-domain-security.yml
- type: Website
  url: https://www.unisound.com
- type: DeveloperPortal
  url: https://ai.unisound.com
- type: Documentation
  url: https://maas.unisound.com/docs
- type: APIReference
  url: https://maas.unisound.com/docs/api/overview
- type: GettingStarted
  url: https://maas.unisound.com/docs/guide/quickstart
- type: Pricing
  url: https://maas.unisound.com/docs/price/overview
- type: TermsOfService
  url: https://maas.unisound.com/docs/protocol/user-agreement
- type: PrivacyPolicy
  url: https://maas.unisound.com/docs/protocol/privacy-policy
- type: Support
  url: https://maas.unisound.com/docs/guide/contact
- type: GitHubOrganization
  url: https://github.com/Unisound
- type: SignUp
  url: https://maas.unisound.com/
- type: RateLimits
  url: rate-limits/unisound-rate-limits.yml
- type: RateLimits
  url: https://maas.unisound.com/docs/api/rate-limits
- type: ChangeLog
  url: https://maas.unisound.com/docs/release/notes
- type: ChangeLog
  url: changelog/unisound-changelog.yml
- type: Packages
  url: packages/unisound-packages.yml
- type: SDKs
  url: packages/unisound-packages.yml
- type: LLMsTxt
  url: llms/unisound-llms.txt
- type: Conformance
  url: conformance/unisound-conformance.yml
- type: ErrorCatalog
  url: errors/unisound-problem-types.yml
- type: Lifecycle
  url: lifecycle/unisound-lifecycle.yml
- type: Authentication
  url: authentication/unisound-authentication.yml
- type: Sandbox
  url: sandbox/unisound-sandbox.yml
- type: Conventions
  url: conventions/unisound-conventions.yml
- type: Plans
  url: plans/unisound-plans.yml
x-enrichment:
  date: '2026-07-21'
  status: enriched
  artifacts_added: 13
  pass: local-v1