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 is listed with 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 20 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

45.8/100 developing ▬ flat Agent 8/100 agent aware Heartbeat 50/100 alive saas Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

3 APIs

Company Artificial Intelligence Speech Recognition Text-to-Speech Voice Cloning LLM OCR Healthcare Machine Learning Voice

Kin Score

Kin Score How this is scored →
scored 2026-11-06 · rubric v0.27.0

Composite quality — 45.8/100 · developing

Contract Quality 0.0 / 21

Developer Ergonomics 11.7 / 17

Access Clarity 13.0 / 17

Operational Transparency 5.5 / 11

Contract Governance 1.9 / 10

Discoverability 6.1 / 9

Regulatory Posture 2.7 / 15

Agent readiness — 8/100 · agent aware

Machine-Readable Contract 0 / 18

Agentic Access Contract 0 / 10

Documented Reversibility 0 / 6

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

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

Pagination 5 / 5

Distinct Operations 3 / 3

MCP Tool Quality 6 / 6

Regulatory Posture applies to this provider. Its tags matched the Health regime, so Regulatory Posture carries 15 points of the composite. If this regime is wrong for your business, say so on your provider repo — the applicability map is public and we will correct it.

Create-or-Update Ergonomics could not be measured. We hold no machine-readable contract for this provider to read, so there is nothing to measure a write surface against. Excluded rather than scored zero: never-measured and measured-empty are different facts. Publishing an OpenAPI is what makes this facet — and several others — scorable at all.

The six quality facets above are damped to 85 points between them, because the conditional facet above carries the other 15. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 85% of its nominal weight, not 100%. The full arithmetic is at apis.io/rating/.

Show this score on your site.

It updates itself when the score changes. Paste this where you link to your API docs:

<a href="https://apis.io/providers/unisound/"><img src="https://apis.io/badge/unisound/card.svg" alt="Unisound on APIs.io — Kin Score by API Evangelist"></a>

Other styles, a README pill and a shields.io endpoint are on the badge page.

Raise your score.

Agent readiness — checks not met, largest first (exact, from this profile):

Machine-Readable Contract +18 pts — api_specs includes an OpenAPI document
MCP Server +12 pts — deployment.mode + probe verdict on the mcp/ manifest, not the pointer; an unprobed slug falls back to authorship
Agentic Access Contract +10 pts — agentic_access artifact present (x-agentic-access), graded by author
Idempotency +9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
A2A Agent Card +8 pts — a2a/-a2a.yml manifest, graded on conformance.grade against A2A 1.0.0
Request/Response Examples +7 pts — share of operations carrying request/response examples; else an Examples / Code Samples link

10 more unmet checks in the Agent Readiness table above.

Kin Score — facets with the most composite points still available (weight × headroom):

Contract Quality scores 0.0 — up to +25.0 composite points
Contract Governance scores 18.2 — up to +9.8 composite points
Operational Transparency scores 50.0 — up to +6.5 composite points

Each check links to what satisfies it. Publish the artifact, or tell us where it already lives, and the score moves on the next scoring run.

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 the provider profile at artifacts.apis.io/unisound/apis.yml: open an issue on github.com/api-evangelist/unisound to ask a question or point us at an artifact you publish. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

Markets this provider is in provisional

The Kin Score Market layer reads a provider inside its market: its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted: not part of the Kin Score or agent readiness.

Market	Position	Depth	Registered MCP server	Declares compatibility
RPA and Document AI (RPA marketplaces, intelligent document processing)	undeclared	-	-	-

Registered MCP server and declares compatibility are report only — not weighted. Undeclared means we found nothing we can read, so there is no number: we never infer integrations.

Standards implemented 1

Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.

The OpenAI Interface

prose — states compatibility; nothing published to check it against

2 core of 338 operations graded · api-commons/models

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...

Unisound API pricing

Prices published by Unisound.

Plan	Price
Pay-as-you-go (按量计费)	—
Model resource packs (模型资源包)	—
Token Plan	—

Plan details, limits and sources →

Rate limits

Text models (u2, u2-med, kimi-k3, glm-5.2) requests: 100 requests per minute
Text models (u2, u2-med, kimi-k3, glm-5.2) tokens: 10000000 tokens per minute
Async speech transcription tasks (v1_audio_asr_tasks, u2-asr): 20 requests per minute

All 9 limits →

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

FinOps 1

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

Unisound Finops

FINOPS

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

DeveloperPortal

GettingStarted

SignUp

Sandbox

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt

LLMsTxt

Design & Contract 4

Pagination, idempotency, versioning, errors, and events

Conformance

ErrorCatalog

Lifecycle

Conventions

Build 3

SDKs, sample code, and the tooling you integrate with

GitHubOrganization

GitHubOrganization

Packages

Packages

SDKs

SDKs

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity

DomainSecurity

Authentication

Authentication

Operate 5

Status, limits, changes, and where to get help

Support

RateLimits

RateLimits

ChangeLog

ChangeLog

Commercial 4

Pricing, plans, and the legal terms of use

Pricing

TermsOfService

PrivacyPolicy

Plans

Company 2

The organization behind the API

BlogRSS

BlogRSS

Website

Website

Source (apis.yml)

aid: unisound
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: false
  label: Hosted service · you call their endpoint
  confidence: medium
  source:
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: unknown
  onboarding: unknown
  trial: false
  try_now: false
  public: false
  label: Unknown
  confidence: low
  source:
  - plans
  - authentication
  - rate-limits
  - security
  - sandbox
  generated: '2026-11-06'
  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: '0.23'
created: '2026-07-17'
modified: '2026-10-06'
tags:
- Company
- Artificial Intelligence
- Speech Recognition
- Text-to-Speech
- Voice Cloning
- LLM
- OCR
- Healthcare
- Machine Learning
- Voice
tags_raw:
- Company
- Artificial Intelligence
- Speech Recognition
- Text-to-Speech
- Voice Cloning
- Large Language Models
- OCR
- Healthcare
- Machine Learning
- Voice
- Machine-Learning
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:
- url: https://www.unisound.com/rss.xml
  type: BlogRSS
- 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

Unisound API — frequently asked questions

Does Unisound have an API?

Yes. APIs.io lists 3 APIs from Unisound, including Unisound Token Hub API, Unisound Shanhai (UniGPT) LLM WebAPI and Unisound AI Open Platform Speech WebAPI.

How do I authenticate with the Unisound API?

Unisound uses bearer-token authentication (apiKey/signature · 3 schemes). The details are profiled on APIs.io as Unisound Authentication.

How much does the Unisound API cost?

APIs.io lists 3 pricing plans for Unisound, with each plan's price, limits and inclusions under Pricing on this page.

Is the Unisound API ready for AI agents?

Unisound has a Kin Score of 45.8 out of 100 (developing) and an Agent Readiness score of 7.9 (agent-aware), scored by API Evangelist on 2026-11-06.

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/unisound"

All providers

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

Every operation they expose

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

How their score was established

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

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

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.