From cf3c071a4a647f19ab9bcb24fe8dee916f7846ec Mon Sep 17 00:00:00 2001 From: karamouche Date: Tue, 10 Feb 2026 15:40:38 -0500 Subject: [PATCH] Added a note about the maximum duration of realtime transcription sessions (3 hours) --- chapters/limits-and-specifications/concurrency.mdx | 4 ++++ chapters/limits-and-specifications/supported-formats.mdx | 4 +++- chapters/live-stt/quickstart.mdx | 4 ++++ 3 files changed, 11 insertions(+), 1 deletion(-) diff --git a/chapters/limits-and-specifications/concurrency.mdx b/chapters/limits-and-specifications/concurrency.mdx index 64b7abc..7349f5a 100644 --- a/chapters/limits-and-specifications/concurrency.mdx +++ b/chapters/limits-and-specifications/concurrency.mdx @@ -29,6 +29,10 @@ The value listed below are default values. We can provide high concurrencies bas This refers to the maximum number of transcription (pre-recorder or real-time) that a user can process at the same time. For asynchronous transcriptions, Paid plan users can queue up to 300 requests, but only will still have 25 max processed concurrently. +- **Realtime session duration** : (all plans) + + A single realtime (live) transcription session cannot exceed **3 hours**. After 3 hours, the session will be terminated. For longer events, start a new session when approaching the limit. + - **API level rate limit** : (same for every user) Which is the number of API calls that a user can make within a particular time frame. diff --git a/chapters/limits-and-specifications/supported-formats.mdx b/chapters/limits-and-specifications/supported-formats.mdx index 9323b0d..2ff091e 100644 --- a/chapters/limits-and-specifications/supported-formats.mdx +++ b/chapters/limits-and-specifications/supported-formats.mdx @@ -15,7 +15,7 @@ Those limits will be gradually lifted to ensure the full stability and performan -- **Audio length**: The maximum length of audio that can be transcribed in a single request is currently +- **Audio length (pre-recorded)**: The maximum length of audio that can be transcribed in a single request is currently 135 minutes. Attempts to transcribe longer audio files will result in an error. Direct YouTube links are limited to 120 minutes instead of 135 minutes. @@ -23,6 +23,8 @@ Direct YouTube links are limited to 120 minutes instead of 135 minutes. We support up to 4h15 audio length for enterprise plans. +- **Realtime session duration**: For [live (realtime) transcription](/chapters/live-stt/quickstart), a single WebSocket session cannot exceed **3 hours**. The session will be terminated after 3 hours; for longer events, start a new session before reaching the limit. + - **File size**: Audio files must not exceed 1000 MB in size. Larger files will not be accepted by the API. ### Splitting oversize audio files diff --git a/chapters/live-stt/quickstart.mdx b/chapters/live-stt/quickstart.mdx index ffe1369..e58b35b 100644 --- a/chapters/live-stt/quickstart.mdx +++ b/chapters/live-stt/quickstart.mdx @@ -6,6 +6,10 @@ description: How to transcribe live audio with Gladia's Real-time speech-to-text import LiveFlowFull from "/snippets/live-flow-full.mdx"; import Samples from '/snippets/samples.mdx'; + +A single realtime transcription session cannot exceed **3 hours**. For longer events, start a new session before reaching the limit. See [Concurrency and rate limits](/chapters/limits-and-specifications/concurrency) and [Supported files & duration](/chapters/limits-and-specifications/supported-formats) for details. + + Want to know more about a specific feature? Check out our [Features chapter](/chapters/live-stt/features) for more details.