# Gladia

> Gladia is a state-of-the-art audio transcription and intelligence provider. We offer a simple API to get transcription from your audios and videos, in both Real-time and asynchronous ways, with audio intelligence tools to extract, analyze and understand data from your audios.

- [Welcome to Gladia](https://docs.gladia.io/chapters/introduction/index.md): The most reliable state-of-the-art Speech-To-Text API provider
- [Getting started](https://docs.gladia.io/chapters/introduction/getting-started.md): Setup your Gladia account and start using the most reliable state-of-the-art Speech-To-Text API
- [Models](https://docs.gladia.io/chapters/introduction/models.md): Compare Gladia speech-to-text models and choose the right one for your use case.
- [SDK](https://docs.gladia.io/chapters/how-to-use-gladia/sdk.md): Transcribe audio in a few lines with the official Gladia SDKs
- [Playground](https://docs.gladia.io/chapters/how-to-use-gladia/playground.md): Test Gladia models and features in the browser before you integrate
- [CLI](https://docs.gladia.io/chapters/how-to-use-gladia/cli.md): Transcribe audio from your terminal with one install and one command.
- [Gladia MCP](https://docs.gladia.io/chapters/how-to-use-gladia/mcp.md)
- [Benchmarking](https://docs.gladia.io/chapters/how-to-use-gladia/benchmarking.md): A clear 5-step method to compare speech-to-text accuracy fairly
- [GladiaFlow](https://docs.gladia.io/chapters/how-to-use-gladia/gladia-flow.md): Real-time voice dictation for your desktop.
- [Quickstart](https://docs.gladia.io/chapters/pre-recorded-stt/quickstart.md): How to transcribe pre-recorded audio with Gladia's speech-to-text (STT) API
- [Transcription process & retry policy](https://docs.gladia.io/chapters/pre-recorded-stt/transcription-process.md): How pre-recorded jobs move through the Gladia pipeline, concurrency impact, and when to retry safely
- [Audio Intelligence](https://docs.gladia.io/chapters/pre-recorded-stt/audio-intelligence.md): Turn speech into actionable insights with translation, summarization, entities, chapters, sentiment and more
- [Recommended Parameters by Use Case](https://docs.gladia.io/chapters/pre-recorded-stt/recommended-parameters.md): Best parameter configurations for pre-recorded transcription depending on your application (Meeting Recorders, Call Centers, Podcasts, Subtitles, Multilingual Content).
- [Streaming speech-to-text quickstart](https://docs.gladia.io/chapters/live-stt/quickstart.md): Start live transcription with Gladia using the SDK or WebSocket API. Configure audio, receive partial and final transcripts and tune endpointing.
- [Audio Intelligence](https://docs.gladia.io/chapters/live-stt/audio-intelligence.md): Turn speech into actionable insights with translation, summarization, entities, chapters, sentiment and more
- [Endpointing](https://docs.gladia.io/chapters/live-stt/features/endpointing.md): Configure silence thresholds and maximum utterance duration in Gladia live transcription. Understand the latency and completeness tradeoff.
- [Partial transcripts](https://docs.gladia.io/chapters/live-stt/features/partial-transcripts.md): Low-latency streaming transcripts before the final result
- [Recommended Parameters by Use Case](https://docs.gladia.io/chapters/live-stt/recommended-parameters.md): Best parameter configurations for realtime transcription depending on your application (Voice Agents, Meeting Recorders, Call Centers, Subtitles).
- [Automatic language detection for audio](https://docs.gladia.io/chapters/language/language-detection.md): Detect spoken languages in Gladia transcription. Set a candidate language list, understand code switching and choose the right model for your audio.
- [Code switching](https://docs.gladia.io/chapters/language/code-switching.md): Transcribe conversations that mix multiple languages in real time or pre-recorded
- [Supported languages](https://docs.gladia.io/chapters/language/supported-languages.md): All languages supported by Gladia with ISO 639-1 codes and capabilities
- [Speaker diarization for pre-recorded audio](https://docs.gladia.io/chapters/audio-intelligence/speaker-diarization.md): Enable speaker diarization for pre-recorded audio in Gladia. Configure speaker-count hints and read speaker labels, timestamps and limitations.
- [Translation](https://docs.gladia.io/chapters/audio-intelligence/translation.md): Translate your transcriptions & subtitles
- [Export subtitles (SRT/VTT)](https://docs.gladia.io/chapters/audio-intelligence/subtitles.md): Generate caption files directly from transcripts
- [Sentences](https://docs.gladia.io/chapters/audio-intelligence/sentences.md): Semantic sentence segmentation for more readable pre-recorded transcripts
- [Custom vocabulary](https://docs.gladia.io/chapters/audio-intelligence/custom-vocabulary.md): Configure custom vocabulary in Gladia live and pre-recorded transcription. Add pronunciation variants, tune intensity and distinguish custom spelling.
- [Custom spelling](https://docs.gladia.io/chapters/audio-intelligence/custom-spelling.md): Normalize spelling variants to your preferred forms
- [Named Entity Recognition](https://docs.gladia.io/chapters/audio-intelligence/named-entity-recognition.md): The Named Entity Recognition model automatically identifies and categorizes key information in the audio.
- [PII Redaction](https://docs.gladia.io/chapters/audio-intelligence/pii-redaction.md): Automatically detect and redact personally identifiable information in pre-recorded transcripts
- [Sentiment and Emotion Analysis](https://docs.gladia.io/chapters/audio-intelligence/sentiment-analysis.md): Extract sentiments and emotions from the transcript.
- [Summarization](https://docs.gladia.io/chapters/audio-intelligence/summarization.md): Retrieve important information from your audio files
- [Audio-to-LLM](https://docs.gladia.io/chapters/audio-intelligence/audio-to-llm.md): Run your own prompts on a pre-recorded transcript with an LLM - summaries, Q&A, extraction, and more.
- [Custom metadata](https://docs.gladia.io/chapters/audio-intelligence/custom-metadata.md): Attach metadata to transcription jobs for filtering and retrieval
- [Pipecat](https://docs.gladia.io/chapters/integrations/pipecat.md): How to integrate Gladia with Pipecat
- [Livekit](https://docs.gladia.io/chapters/integrations/livekit.md): How to integrate Gladia with LiveKit Agents
- [Vapi](https://docs.gladia.io/chapters/integrations/vapi.md)
- [Recall](https://docs.gladia.io/chapters/integrations/recall.md): How to use Gladia with Recall.ai Meeting Bot
- [Meeting BaaS](https://docs.gladia.io/chapters/integrations/meeting-baas.md): How to integrate Gladia with Meeting BaaS
- [Attendee](https://docs.gladia.io/chapters/integrations/attendee.md): How to integrate Gladia with the Attendee Meeting Bot API
- [Twilio](https://docs.gladia.io/chapters/integrations/twilio.md): How to integrate Gladia with Twilio Media Streams
- [VideoSDK](https://docs.gladia.io/chapters/integrations/videosdk.md): How to integrate Gladia with VideoSDK AI Agents
- [Composio](https://docs.gladia.io/chapters/integrations/composio.md): How to use Gladia with Composio
- [Zapier](https://docs.gladia.io/chapters/integrations/zapier.md): How to use Gladia with Zapier
- [Make](https://docs.gladia.io/chapters/integrations/make.md): How to use Gladia with Make
- [n8n](https://docs.gladia.io/chapters/integrations/n8n.md): How to use Gladia with n8n
- [Gladia CLI](https://docs.gladia.io/chapters/developer-tools/gladia-cli.md): Transcribe audio from your terminal with one install, one command, and no boilerplate
- [Gladia Skills](https://docs.gladia.io/chapters/developer-tools/gladia-skills.md)
- [API rate limits and transcription concurrency](https://docs.gladia.io/chapters/limits-and-specifications/concurrency.md): Check Gladia transcription concurrency, queue capacity and live session duration. Understand 429 responses and how to request more capacity.
- [Multiple channels](https://docs.gladia.io/chapters/limits-and-specifications/multiple-channels.md): Transcribe multi-channel audio and tag utterances by channel
- [Supported files & duration](https://docs.gladia.io/chapters/limits-and-specifications/supported-formats.md): Media files limitations
- [Data retention and zero data retention](https://docs.gladia.io/chapters/limits-and-specifications/data-retention.md): Understand Gladia retention windows for audio, transcripts and metadata, Enterprise zero data retention, callback delivery and retrieval limitations.
- [Quick migration guide: realtime STT from Deepgram to Gladia](https://docs.gladia.io/chapters/migrations/from-deepgram.md): Guide to seamlessly switch your realtime WebSocket transcription from Deepgram's SDK to Gladia's SDK.
- [Quick migration guide: realtime STT from AssemblyAI to Gladia](https://docs.gladia.io/chapters/migrations/from-assembly.md): Guide to seamlessly switch your realtime WebSocket transcription from AssemblyAI's SDK to Gladia's SDK.
- [Live transcription - Migration guide from V1 to V2](https://docs.gladia.io/chapters/live-stt/migration-from-v1.md): Migrate to the latest version of Gladia's real-time speech-to-text API
- [Pre-recorded - Migration guide from V1 to V2](https://docs.gladia.io/chapters/pre-recorded-stt/migration-from-v1.md): Migrate to the latest version of Gladia's pre-recorded speech-to-text API
- [Introduction](https://docs.gladia.io/api-reference/index.md): Technical documentation for Gladia API
- [Authentication](https://docs.gladia.io/api-reference/authentication.md): Use your API key to authenticate your calls
- [Initiate a session](https://docs.gladia.io/api-reference/v2/live/init.md): Initiate a live transcription WebSocket session.
- [Live WebSocket](https://docs.gladia.io/api-reference/v2/live/websocket.md): WebSocket to send audio chunks and receive events.
- [Get result](https://docs.gladia.io/api-reference/v2/live/get.md): Get live transcription's status, parameters and result.
- [List transcriptions](https://docs.gladia.io/api-reference/v2/live/list.md): List all the live transcriptions matching the parameters.
- [Download audio file](https://docs.gladia.io/api-reference/v2/live/get-audio.md): Download the audio file recorded during a live transcription.
- [Delete transcription](https://docs.gladia.io/api-reference/v2/live/delete.md): Delete a live transcription and all its data (audio file, transcription).
- [Start session](https://docs.gladia.io/api-reference/v2/live/webhook/start-session.md): Payload definition for the webhook event `live.start_session`.
- [Start recording](https://docs.gladia.io/api-reference/v2/live/webhook/start-recording.md): Payload definition for the webhook event `live.start_recording`.
- [End recording](https://docs.gladia.io/api-reference/v2/live/webhook/end-recording.md): Payload definition for the webhook event `live.end_recording`.
- [End session](https://docs.gladia.io/api-reference/v2/live/webhook/end-session.md): Payload definition for the webhook event `live.end_session`.
- [Transcript](https://docs.gladia.io/api-reference/v2/live/callback/transcript.md): Payload definition for the callback event `live.transcript`.
- [Speech Start](https://docs.gladia.io/api-reference/v2/live/callback/speech-start.md): Payload definition for the callback event `live.speech_start`.
- [Speech End](https://docs.gladia.io/api-reference/v2/live/callback/speech-end.md): Payload definition for the callback event `live.speech_end`.
- [Translation](https://docs.gladia.io/api-reference/v2/live/callback/translation.md): Payload definition for the callback event `live.translation`.
- [Named Entity Recognition](https://docs.gladia.io/api-reference/v2/live/callback/named-entity-recognition.md): Payload definition for the callback event `live.named_entity_recognition`.
- [Sentiment Analysis](https://docs.gladia.io/api-reference/v2/live/callback/sentiment-analysis.md): Payload definition for the callback event `live.sentiment_analysis`.
- [Post Transcript](https://docs.gladia.io/api-reference/v2/live/callback/post-transcript.md): Payload definition for the callback event `live.post_transcript`.
- [Final transcript](https://docs.gladia.io/api-reference/v2/live/callback/post-final-transcript.md): Payload definition for the callback event `live.post_final_transcript`.
- [Summarization](https://docs.gladia.io/api-reference/v2/live/callback/post-summarization.md): Payload definition for the callback event `live.post_summarization`.
- [Audio chunk acknowledge (ack)](https://docs.gladia.io/api-reference/v2/live/callback/audio-chunk-ack.md): Payload definition for the [`audio_chunk`](/api-reference/v2/live/action/audio-chunk) acknowledgment.
- [Stop recording acknowledge (ack)](https://docs.gladia.io/api-reference/v2/live/callback/stop-recording-ack.md): Payload definition for the [`stop_recording`](/api-reference/v2/live/action/stop-recording) acknowledgment.
- [Start session](https://docs.gladia.io/api-reference/v2/live/callback/start-session.md): Payload definition for the callback event `live.start_session`.
- [Start recording](https://docs.gladia.io/api-reference/v2/live/callback/start-recording.md): Payload definition for the callback event `live.start_recording`.
- [End recording](https://docs.gladia.io/api-reference/v2/live/callback/end-recording.md): Payload definition for the callback event `live.end_recording`.
- [End session](https://docs.gladia.io/api-reference/v2/live/callback/end-session.md): Payload definition for the callback event `live.end_session`.
- [Upload a file](https://docs.gladia.io/api-reference/v2/upload/audio-file.md): Upload a file for use in a pre-recorded job.
- [Initiate a transcription](https://docs.gladia.io/api-reference/v2/pre-recorded/init.md): Initiate a pre-recorded transcription job. Use the returned `id` and the [GET /v2/pre-recorded/:id](/api-reference/v2/pre-recorded/get) endpoint to obtain the results.
- [Get result](https://docs.gladia.io/api-reference/v2/pre-recorded/get.md): Get pre-recorded transcription's status, parameters and result.
- [List transcriptions](https://docs.gladia.io/api-reference/v2/pre-recorded/list.md): List all the pre-recorded transcriptions matching the parameters.
- [Download audio file](https://docs.gladia.io/api-reference/v2/pre-recorded/get-audio.md): Download the audio file used on a pre-recorded transcription.
- [Delete transcription](https://docs.gladia.io/api-reference/v2/pre-recorded/delete.md): Delete a pre-recorded transcription and all its data (audio file, transcription).
- [Created](https://docs.gladia.io/api-reference/v2/pre-recorded/webhook/created.md): Payload definition for the webhook event `transcription.created`.
- [Success](https://docs.gladia.io/api-reference/v2/pre-recorded/webhook/success.md): Payload definition for the webhook event `transcription.success`.
- [Error](https://docs.gladia.io/api-reference/v2/pre-recorded/webhook/error.md): Payload definition for the webhook event `transcription.error`.
- [Success](https://docs.gladia.io/api-reference/v2/pre-recorded/callback/success.md): Payload definition for the callback event `transcription.success`.
- [Error](https://docs.gladia.io/api-reference/v2/pre-recorded/callback/error.md): Payload definition for the callback event `transcription.error`.
- [Initiate a transcription](https://docs.gladia.io/api-reference/v2/transcription/init.md): (Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/init).<br/><br/>Initiate a pre-recorded transcription job. Use the returned id and the [GET /v2/transcription/:id](/api-reference/v2/transcription/get) endpoint to obtain the results.
- [Get result](https://docs.gladia.io/api-reference/v2/transcription/get.md): (Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/get).<br/><br/>Get transcription's status, parameters and result.
- [List transcriptions](https://docs.gladia.io/api-reference/v2/transcription/list.md): (Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/list).<br/><br/>List all the transcriptions matching the parameters.
- [Download audio file](https://docs.gladia.io/api-reference/v2/transcription/get-audio.md): (Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/get-audio).<br/><br/>Download the audio file used on a transcription.
- [Delete transcription](https://docs.gladia.io/api-reference/v2/transcription/delete.md): (Deprecated) Prefer the more specific [pre-recorded endpoint](/api-reference/v2/pre-recorded/delete).<br/><br/>Delete a transcription and all its data (audio file, transcription).

## OpenAPI Specs

- [openapi](https://api.gladia.io/openapi.json)
- [openapi](/openapi)

## AsyncAPI Specs

- [asyncapi](/asyncapi.yaml)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.