Gradium

Gradium is a voice AI lab (Paris and Silicon Valley) building audio language models for real-time, low-latency Text-to-Speech, Speech-to-Text, and Speech-to-Speech translation. Founded in 2025 by ex-DeepMind / Meta / Kyutai researchers (Neil Zeghidour, Olivier Teboul, Laurent Mazaré, Alexandre Défossez), Gradium exposes a developer API over REST and WebSocket featuring instant voice cloning from a 10-second sample, custom pronunciation dictionaries, sub-300ms time-to-first-token streaming, and multilingual support (English, French, German, Spanish, Portuguese). It ships first-party Python and Rust SDKs, a `gradium` CLI, and the open-source gradbot voice-agent framework, and is available on AWS Marketplace / SageMaker. Backed by a $70M seed round with participation from Amplify Partners, Eric Schmidt, and Xavier Niel.

Gradium publishes 6 API contracts indexed on the APIs.io network, including Metering API, Pronunciations API, S2S API, and 3 more. Tagged areas include Company, Artificial Intelligence, Voice AI, Text-to-Speech, and Speech-to-Text.

The Gradium catalog on APIs.io includes 1 event-driven AsyncAPI specification and 1 Spectral governance ruleset.

Gradium’s developer surface includes documentation, API reference, getting-started guide, CLI, authentication, changelog, sandbox, and 31 more developer resources.

🌐 Visit website 📡 Profile data on GitHub

56.5/100 strong ▬ flat Agent 30/100 agent ready Front door AI 4/6 moderate Heartbeat 100/100 alive saas Full breakdown ↓
scored 2026-11-06 · rubric v0.27.0 · Show this score on your site →

AccessFreemiumSelf serve⚡ Free to try

1 published contract 4 Agent Skills

Company Artificial Intelligence Voice AI Text-to-Speech Speech-to-Text Speech to Speech Voice Cloning Audio Real-Time Streaming WebSocket Developer API Voice Agents Real-Time

Kin Score

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

Composite quality — 56.5/100 · strong

Contract Quality 9.9 / 19

Developer Ergonomics 11.7 / 15

Access Clarity 10.7 / 15

Operational Transparency 3.3 / 10

Contract Governance 1.6 / 9

Discoverability 5.5 / 8

Regulatory Posture 2.9 / 15

Create-or-Update Ergonomics 0.0 / 10

Agent readiness — 30/100 · agent ready

Machine-Readable Contract 18 / 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 6 / 6

Agent Skills 5 / 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 AI & Biometrics 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 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.

The six quality facets above are damped to 75 points between them, because the conditional facet above carries the other 25. That is why each facet's contribution is shown against a damped maximum: raising a quality facet moves the composite by 75% 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/gradium/"><img src="https://apis.io/badge/gradium/card.svg" alt="Gradium 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):

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
Registration Without a Human +6 pts — a `registration_endpoint` in the served RFC 8414 / OIDC discovery document

7 more unmet checks in the Agent Readiness table above.

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

Contract Quality scores 53.0 — up to +11.8 composite points
Contract Governance scores 18.2 — up to +9.8 composite points
Operational Transparency scores 34.2 — up to +8.6 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/gradium/apis.yml: open an issue on github.com/api-evangelist/gradium 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
Speech and Voice AI	covered	44.1	-	-

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 2

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.

WebSockets

tagged — the provider's own APIs.json carries the standard as a tag; implementation not verified

OpenAPI

measured — observed by APIs.io (published)

APIs 6

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

Gradium Metering API

The metering API from Gradium — 1 operation(s) for metering.

Gradium Pronunciations API

Manage pronunciation dictionaries for custom text rewriting

Gradium S2S API

The S2S API from Gradium — 1 operation(s) for s2s.

Gradium STT API

Speech-to-Text endpoints for converting audio to text

Gradium TTS API

Text-to-Speech endpoints for converting text to audio

Gradium Voices API

Manage custom voice clones

Open Collections 6

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

Gradium metering API

OPEN COLLECTION

Gradium metering Pronunciations API

OPEN COLLECTION

Gradium metering S2S API

OPEN COLLECTION

Gradium metering STT API

OPEN COLLECTION

Gradium metering TTS API

OPEN COLLECTION

Gradium metering Voices API

OPEN COLLECTION

Agent Skills 4

Packaged agent skills for driving this provider's APIs from an AI assistant.

Check Gradium credit balance

AGENT SKILL

Manage Gradium custom voices

AGENT SKILL

Manage Gradium pronunciation dictionaries

AGENT SKILL

Stream Gradium text-to-speech

AGENT SKILL

Gradium API pricing

Prices published by Gradium, read 2026-10-28 from gradium.ai/pricing.

Plan	Price
Free	$0/mo Includes: 45k credits/mo
XS	$12/mo Includes: 225k credits/mo
S	$39/mo Includes: 900k credits/mo
M	$312/mo Includes: 9M credits/mo
L	$1,480/mo Includes: 45M credits/mo
Enterprise	Custom Includes: Unlimited

Plan details, limits and sources →

Billed by: credits · FinOps profile →

Pricing Plans 2

Published pricing tiers and plan structures.

Gradium Plans Pricing

6 plans

PLANS

Gradium Price Estimates

0 plans

PLANS

Service Levels 1

Uptime the provider promises or reports, as SLA4OAI. Read from its own pages; APIs.io runs no monitors.

Gradium

SLA

FinOps 1

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

Gradium Finops

FINOPS

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Gradium Speech Streaming API

AsyncAPI capture of Gradium's real-time speech WebSocket surface (TTS, STT, and Speech-to-Speech). Generated by API Evangelist from the documented WebSocket lifecycle and messag...

ASYNCAPI

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Gradium API Rules

49 rules · 45 errors 1 warnings 3 info

SPECTRAL

OpenAPI Overlays 1

Overlays applied on top of this provider's contracts. Each card says who wrote it: a document the provider publishes, or one API Evangelist derived or generated.

Gradium Openapi Overlay

3 actions · security · gradium-openapi-original.json

DERIVED

Security Posture 2

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

Gradium Authentication

apiKey/bearer-token · 2 schemes

SECURITY

Gradium Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 5

Portal, sign-up, and the first successful call

DeveloperPortal

GettingStarted

Sandbox

SignUp

Login

Documentation 4

Reference material describing how the API behaves

Documentation

APIReference

OpenAPI

AsyncAPI

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

LLMsTxt

LLMsTxt

X-MCPServerCandidate

X-MCPServerCandidate

AgentSkill

AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions

ErrorCatalog

Conformance

DataModel

Lifecycle

Build 4

SDKs, sample code, and the tooling you integrate with

SDKs

SDKs

Packages

Packages

CLI

CLI

GitHubOrganization

GitHubOrganization

Access & Security 3

Authentication, authorization, and security posture

Authentication

Authentication

DomainSecurity

DomainSecurity

TrustCenter

TrustCenter

Operate 6

Status, limits, changes, and where to get help

Deprecation

ChangeLog

RateLimits

StatusPage

Support

Community

Commercial 4

Pricing, plans, and the legal terms of use

Plans

Pricing

TermsOfService

PrivacyPolicy

Company 3

The organization behind the API

BlogRSS

BlogRSS

Website

Website

Blog

Blog

Other 1

Properties that don't map to a standard resource type

Overlay

Overlay

Source (apis.yml)

aid: gradium
name: Gradium
description: Gradium is a voice AI lab (Paris and Silicon Valley) building audio language models for real-time, low-latency
  Text-to-Speech, Speech-to-Text, and Speech-to-Speech translation. Founded in 2025 by ex-DeepMind / Meta / Kyutai researchers
  (Neil Zeghidour, Olivier Teboul, Laurent Mazaré, Alexandre Défossez), Gradium exposes a developer API over REST and WebSocket
  featuring instant voice cloning from a 10-second sample, custom pronunciation dictionaries, sub-300ms time-to-first-token
  streaming, and multilingual support (English, French, German, Spanish, Portuguese). It ships first-party Python and Rust
  SDKs, a `gradium` CLI, and the open-source gradbot voice-agent framework, and is available on AWS Marketplace / SageMaker.
  Backed by a $70M seed round with participation from Amplify Partners, Eric Schmidt, and Xavier Niel.
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
  gated: none
  gated_source:
  - onboarding
  label: Freemium · Self-serve signup
  confidence: medium
  source:
  - plans
  - authentication
  - security
  generated: '2026-11-06'
  method: derived
image: https://gradium.ai/assets/dots_1200.png
url: https://raw.githubusercontent.com/api-evangelist/gradium/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- amplify-partners
x-tier: enriched
x-tier-reason: portfolio-lead
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-10-06'
x-docs-platform: mintlify
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-10-03
x-docs-hosting: vercel
tags:
- Company
- Artificial Intelligence
- Voice AI
- Text-to-Speech
- Speech-to-Text
- Speech to Speech
- Voice Cloning
- Audio
- Real-Time Streaming
- WebSocket
- Developer API
- Voice Agents
- Real-Time
tags_raw:
- Company
- Ai Ml
- Voice AI
- Text-to-Speech
- Speech-to-Text
- Speech-to-Speech
- Voice Cloning
- Audio
- Real-Time Streaming
- WebSocket
- Developer API
- Voice Agents
- Real-Time
apis:
- aid: gradium:gradium-metering-api
  name: Gradium Metering API
  description: The metering API from Gradium — 1 operation(s) for metering.
  humanURL: https://docs.gradium.ai/api-reference/introduction
  baseURL: https://api.gradium.ai/api
  tags:
  - Metering
  tags_raw:
  - metering
  properties:
  - type: OpenAPI
    url: openapi/gradium-metering-api-openapi.yml
  - type: Documentation
    url: https://docs.gradium.ai/
  - type: APIReference
    url: https://docs.gradium.ai/api-reference/introduction
  - type: Authentication
    url: authentication/gradium-authentication.yml
- aid: gradium:gradium-pronunciations-api
  name: Gradium Pronunciations API
  description: Manage pronunciation dictionaries for custom text rewriting
  humanURL: https://docs.gradium.ai/api-reference/introduction
  baseURL: https://api.gradium.ai/api
  tags:
  - Pronunciations
  properties:
  - type: OpenAPI
    url: openapi/gradium-pronunciations-api-openapi.yml
  - type: Documentation
    url: https://docs.gradium.ai/
  - type: APIReference
    url: https://docs.gradium.ai/api-reference/introduction
  - type: Authentication
    url: authentication/gradium-authentication.yml
- aid: gradium:gradium-s2s-api
  name: Gradium S2S API
  description: The S2S API from Gradium — 1 operation(s) for s2s.
  humanURL: https://docs.gradium.ai/api-reference/introduction
  baseURL: https://api.gradium.ai/api
  tags:
  - S2S
  properties:
  - type: OpenAPI
    url: openapi/gradium-s2s-api-openapi.yml
  - type: Documentation
    url: https://docs.gradium.ai/
  - type: APIReference
    url: https://docs.gradium.ai/api-reference/introduction
  - type: Authentication
    url: authentication/gradium-authentication.yml
- aid: gradium:gradium-stt-api
  name: Gradium STT API
  description: Speech-to-Text endpoints for converting audio to text
  humanURL: https://docs.gradium.ai/api-reference/introduction
  baseURL: https://api.gradium.ai/api
  tags:
  - STT
  properties:
  - type: OpenAPI
    url: openapi/gradium-stt-api-openapi.yml
  - type: Documentation
    url: https://docs.gradium.ai/
  - type: APIReference
    url: https://docs.gradium.ai/api-reference/introduction
  - type: Authentication
    url: authentication/gradium-authentication.yml
- aid: gradium:gradium-tts-api
  name: Gradium TTS API
  description: Text-to-Speech endpoints for converting text to audio
  humanURL: https://docs.gradium.ai/api-reference/introduction
  baseURL: https://api.gradium.ai/api
  tags:
  - Text-to-Speech
  tags_raw:
  - TTS
  properties:
  - type: OpenAPI
    url: openapi/gradium-tts-api-openapi.yml
  - type: Documentation
    url: https://docs.gradium.ai/
  - type: APIReference
    url: https://docs.gradium.ai/api-reference/introduction
  - type: Authentication
    url: authentication/gradium-authentication.yml
- aid: gradium:gradium-voices-api
  name: Gradium Voices API
  description: Manage custom voice clones
  humanURL: https://docs.gradium.ai/api-reference/introduction
  baseURL: https://api.gradium.ai/api
  tags:
  - Voice
  tags_raw:
  - Voices
  properties:
  - type: OpenAPI
    url: openapi/gradium-voices-api-openapi.yml
  - type: Documentation
    url: https://docs.gradium.ai/
  - type: APIReference
    url: https://docs.gradium.ai/api-reference/introduction
  - type: Authentication
    url: authentication/gradium-authentication.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Plans
  url: plans/gradium-plans-pricing.yml
- url: https://gradium.ai/blog/feed.xml
  type: BlogRSS
- type: Website
  url: https://gradium.ai
- type: DeveloperPortal
  url: https://docs.gradium.ai/
- type: Documentation
  url: https://docs.gradium.ai/
- type: APIReference
  url: https://docs.gradium.ai/api-reference/introduction
- type: GettingStarted
  url: https://docs.gradium.ai/guides/installation
- type: OpenAPI
  url: openapi/_original/gradium-openapi-original.json
- type: LLMsTxt
  url: llms/gradium-llms.txt
- type: SDKs
  url: packages/gradium-packages.yml
- type: Packages
  url: packages/gradium-packages.yml
- type: CLI
  url: cli/gradium-cli.yml
- type: X-MCPServerCandidate
  url: mcp/gradium-mcp.yml
  note: 'Renamed from MCPServer 2026-09-03 (roadmap#247): the manifest self-describes as status: candidate — a tool list derived
    from the published API contracts, not an existing server. The scorer already read the manifest and reported mcp_server
    correctly; the MCPServer type was crediting the artifact-type surfaces with a server that does not exist.'
- type: Authentication
  url: authentication/gradium-authentication.yml
- type: Conventions
  url: conventions/gradium-conventions.yml
- type: ErrorCatalog
  url: errors/gradium-error-codes.yml
- type: Conformance
  url: conformance/gradium-conformance.yml
- type: DataModel
  url: data-model/gradium-data-model.yml
- type: Overlay
  url: overlays/gradium-openapi-overlay.yaml
- type: AsyncAPI
  url: asyncapi/gradium-speech-asyncapi.yml
- type: Lifecycle
  url: lifecycle/gradium-lifecycle.yml
- type: Deprecation
  url: lifecycle/gradium-lifecycle.yml
- type: ChangeLog
  url: changelog/gradium-changelog.yml
- type: DomainSecurity
  url: security/gradium-domain-security.yml
- type: AgentSkill
  url: skills/_index.yml
- type: RateLimits
  url: https://docs.gradium.ai/guides/limits
- type: StatusPage
  url: https://gradium.statuspage.io/
- type: TrustCenter
  url: https://trust.gradium.ai/
- type: Sandbox
  url: https://studio.gradium.ai/
- type: Blog
  url: https://gradium.ai/blog
- type: GitHubOrganization
  url: https://github.com/gradium-ai
- type: Support
  url: mailto:support@gradium.ai
- type: Community
  url: https://discord.com/invite/bcysuPRzXE
- type: Pricing
  url: https://gradium.ai/pricing
- type: SignUp
  url: https://studio.gradium.ai/platform/subscription
- type: Login
  url: https://accounts.gradium.ai/sign-in
- type: TermsOfService
  url: https://www.gradium.ai/terms-of-service
- type: PrivacyPolicy
  url: https://www.gradium.ai/privacy
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence

Gradium API — frequently asked questions

Does Gradium have an API?

Yes. APIs.io lists 6 APIs from Gradium, including Gradium Metering API, Gradium Pronunciations API and Gradium S2S API, and 3 more.

Is there an OpenAPI specification for the Gradium API?

Yes. APIs.io indexes 6 OpenAPI specifications for Gradium, each linked for download from this page.

How do I authenticate with the Gradium API?

Gradium uses bearer-token authentication (apiKey/bearer-token · 2 schemes). The details are profiled on APIs.io as Gradium Authentication.

How much does the Gradium API cost?

Gradium publishes its prices; its Free plan is $0/mo as of 2026-10-28. APIs.io lists 6 pricing plans for Gradium, with each plan's price, limits and inclusions under Pricing on this page.

Is the Gradium API ready for AI agents?

Gradium has a Kin Score of 56.5 out of 100 (strong) and an Agent Readiness score of 29.8 (agent-ready), 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/gradium"

All providers

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

Every operation they expose

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

How their score was established

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