---
title: Limits
sidebar_label: Limits
sidebar_position: 3
description: "Size, duration, and value limits for audio requests and sessions, and what happens when you go over them."
---

# Limits

This page lists the limits of each audio request and session, and what you get when you go over one. Request rates and monthly quotas are workspace settings, covered in [Rate limits and quotas](#rate-limits-and-quotas).

<SectionTab as="h2" sectionId="transcription">Transcription</SectionTab>

These limits apply to file transcription and realtime sessions:

| Limit | Value | Over the limit | Details |
| --- | --- | --- | --- |
| Audio URL length (`file_url`) | 2,083 characters | Validation error | [File transcription](/studio/audio/speech-to-text/transcribe-files#choose-input) |
| Uploaded file (`file_id`) |  | Upload rejected | [File transcription](/studio/audio/speech-to-text/transcribe-files#choose-input) |
| Context window, shared by the audio and `context_bias` | 65,536 tokens | `400` error, nothing is cut | [Limits and errors](/studio/audio/speech-to-text/bias-context-and-vocabulary#limits-and-errors) |
| Timestamps | Per segment only: `timestamp_granularities=segment` | `word` returns a `400` error | [Timestamps](/studio/audio/speech-to-text/transcribe-files#timestamps) |
| Speaker references | Up to 8 clips, 3 to 15 seconds each, with `diarize` set to `true` | The request is rejected with a `400` error: "At most 8 speaker references are supported, got \{n\}". | [Name speakers with reference clips](/studio/audio/speech-to-text/diarize-speakers#speaker-references) |
| Streaming delay (`target_streaming_delay_ms`) | Any integer from 80 to 1200, or 2400 | `error` event | [Control latency](/studio/audio/speech-to-text/transcribe-in-realtime#control-latency) |

<SectionTab as="h2" sectionId="speech-generation">Speech generation</SectionTab>

These limits apply to the values a speech request accepts:

| Limit | Value | Over the limit | Details |
| --- | --- | --- | --- |
| `expressiveness` |  | `422` validation error | [Expressiveness](/studio/audio/text-to-speech/generate-speech#expressiveness) |
| Phonemes in `phoneme_hints` | A closed list of 50 phonemes | `422` error listing the accepted phonemes | [Phonemes](/studio/audio/text-to-speech/custom-pronunciation#phonemes) |
| Emotion tags | 34 values | No error: the tag isn't spoken, and has no documented effect | [Supported emotions](/studio/audio/text-to-speech/emotion-tags#supported-emotions) |
| Pace tags | `slow` or `fast` | No error: the tag isn't spoken, and has no documented effect | [Pace tags](/studio/audio/text-to-speech/emotion-tags#pace-tags) |
| Voice cloning reference clip | A few seconds to a few minutes | `400` error for a file that isn't MP3 or WAV | [Prepare a reference clip](/studio/audio/text-to-speech/voice-cloning#prepare-a-reference-clip) |

<SectionTab as="h2" sectionId="audio-in-chat">Audio in chat completions</SectionTab>

This limit applies to chat requests that carry audio inline:

| Limit | Value | Over the limit | Details |
| --- | --- | --- | --- |
| Request body with `input_audio` |  | `429` error, `Rate limit exceeded` | [Audio in chat completions](/studio/audio/audio-in-chat) |

<SectionTab as="h2" sectionId="voice-agents">Voice agents</SectionTab>

Webhook deliveries to your endpoint follow these limits:

| Limit | Value | Details |
| --- | --- | --- |
| Webhook response time | Your endpoint must answer within 10 seconds | [Delivery and retries](/studio/audio/voice-agents/webhooks#delivery-and-retries) |
| Webhook attempts | Up to 3 in total, on 5xx and 429 responses and on network errors | [Delivery and retries](/studio/audio/voice-agents/webhooks#delivery-and-retries) |

<SectionTab as="h2" sectionId="rate-limits-and-quotas">Rate limits and quotas</SectionTab>

Request rates and monthly quotas are set per workspace, and shared by all its API keys. See [Workspace usage and limits](/admin/workspaces/usage-limits#rate-limits).

<SectionTab as="h2" sectionId="going-further">Going further</SectionTab>

<UsefullLinkContainer>
  <LinkCard href="/studio/audio/specs-and-limits/audio-formats" title="Audio formats" />
  <LinkCard href="/studio/audio/concepts/latency" title="Latency" />
  <LinkCard href="/studio/audio/speech-to-text/troubleshooting" title="Speech to Text troubleshooting" />
  <LinkCard href="/studio/audio/text-to-speech/troubleshooting" title="Text to Speech troubleshooting" />
</UsefullLinkContainer>