Gladia website screenshot

Gladia

Gladia is an AI audio infrastructure platform that offers speech-to-text transcription via both REST and WebSocket APIs, supporting asynchronous pre-recorded audio processing and real-time live transcription. The platform provides speaker diarization, automatic language detection across 100+ languages, word-level timestamps, and audio intelligence features powered by large language models. Authentication uses an API key passed via the x-gladia-key HTTP header against the base URL https://api.gladia.io/v2/. Gladia offers a free tier with 10 hours per month, metered paid plans starting at $0.61/hour for async and $0.75/hour for real-time, and custom enterprise pricing with zero data retention and SLA guarantees.

2 APIs 0 Features
Speech-to-TextTranscriptionAudio IntelligenceReal-TimeSpeaker DiarizationTranslationWebSocketREST

APIs

Gladia Pre-recorded (Async) API

REST API for submitting pre-recorded audio files for asynchronous transcription with speaker diarization, language detection, word-level timestamps, and audio intelligence enric...

Gladia Live (Real-time) API

WebSocket API for real-time live audio transcription with sub-second latency, supporting multi-language detection, live speaker diarization, and streaming audio intelligence. In...

Pricing Plans

Gladia Plans Pricing

3 plans

PLANS

Rate Limits

Gladia Rate Limits

8 limits

RATE LIMITS

FinOps

Gladia Finops

FINOPS

Semantic Vocabularies

Gladia Context

0 classes · 30 properties

JSON-LD

Example Payloads

Gladia Initiate Transcription

11 fields

EXAMPLE

Gladia Live Session Config

7 fields

EXAMPLE

Gladia Upload Audio Url

1 fields

EXAMPLE

Resources

🔗
Website
Website
🔗
Documentation
Documentation
👥
GitHubOrganization
GitHubOrganization
🔗
LinkedIn
LinkedIn
🔗
X
X
📰
Blog
Blog
📄
ChangeLog
ChangeLog
💰
Pricing
Pricing
🟢
StatusPage
StatusPage
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps
🔗
OpenAPI
OpenAPI
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
JSONSchema
JSONSchema
🔗
Vocabulary
Vocabulary
🔗
JSONLDContext
JSONLDContext

Sources

Raw ↑
aid: gladia
name: Gladia
type: Index
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
url: https://raw.githubusercontent.com/api-evangelist/gladia/refs/heads/main/apis.yml
created: 2026-06-12
modified: 2026-06-12
specificationVersion: '0.19'
description: 'Gladia is an AI audio infrastructure platform that offers speech-to-text transcription via both REST and WebSocket
  APIs, supporting asynchronous pre-recorded audio processing and real-time live transcription. The platform provides speaker
  diarization, automatic language detection across 100+ languages, word-level timestamps, and audio intelligence features
  powered by large language models. Authentication uses an API key passed via the x-gladia-key HTTP header against the base
  URL https://api.gladia.io/v2/. Gladia offers a free tier with 10 hours per month, metered paid plans starting at $0.61/hour
  for async and $0.75/hour for real-time, and custom enterprise pricing with zero data retention and SLA guarantees.

  '
tags:
- Speech-to-Text
- Transcription
- Audio Intelligence
- Real-Time
- Speaker Diarization
- Translation
- WebSocket
- REST
apis:
- name: Gladia Pre-recorded (Async) API
  description: 'REST API for submitting pre-recorded audio files for asynchronous transcription with speaker diarization,
    language detection, word-level timestamps, and audio intelligence enrichments.

    '
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.gladia.io/chapters/introduction
  baseURL: https://api.gladia.io/v2/
  tags:
  - Speech-to-Text
  - Transcription
  - REST
  - Asynchronous
  properties:
  - type: Documentation
    url: https://docs.gladia.io/chapters/introduction
  - type: OpenAPI
    url: https://docs.gladia.io/api-reference
- name: Gladia Live (Real-time) API
  description: 'WebSocket API for real-time live audio transcription with sub-second latency, supporting multi-language detection,
    live speaker diarization, and streaming audio intelligence. Individual sessions are capped at 3 hours.

    '
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://docs.gladia.io/chapters/introduction
  baseURL: wss://api.gladia.io/
  tags:
  - Speech-to-Text
  - Real-Time
  - WebSocket
  - Live Transcription
  properties:
  - type: Documentation
    url: https://docs.gladia.io/chapters/introduction
  - type: AsyncAPI
    url: https://github.com/gladiaio/docs
common:
- type: Website
  url: https://www.gladia.io/
- type: Documentation
  url: https://docs.gladia.io/
- type: GitHubOrganization
  url: https://github.com/gladiaio
- type: LinkedIn
  url: https://www.linkedin.com/company/gladia-io
- type: X
  url: https://x.com/gladia_io
- type: Blog
  url: https://www.gladia.io/blog
- type: ChangeLog
  url: https://www.gladia.io/changelog
- type: Pricing
  url: https://www.gladia.io/pricing
- type: StatusPage
  url: https://status.gladia.io/
- type: Plans
  url: plans/gladia-plans-pricing.yml
- type: RateLimits
  url: rate-limits/gladia-rate-limits.yml
- type: FinOps
  url: finops/gladia-finops.yml
- type: OpenAPI
  url: openapi/gladia-control-api-openapi.yml
- type: JSONSchema
  url: json-schema/gladia-init-transcription-request.json
- type: JSONSchema
  url: json-schema/gladia-audio-upload-response.json
- type: JSONSchema
  url: json-schema/gladia-init-pre-recorded-transcription-response.json
- type: JSONSchema
  url: json-schema/gladia-diarization-config.json
- type: JSONSchema
  url: json-schema/gladia-live-event-payload.json
- type: Vocabulary
  url: vocabulary/gladia-vocabulary.yml
- type: JSONLDContext
  url: json-ld/gladia-context.jsonld
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com