> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tryopencomputer.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Set up speech caching

> Reuse MiniMax TTS audio and inspect or invalidate cached phrases.

Speech caching reuses generated audio for repeated synthesis requests. It is separate from the uploaded-recording library and from recordings of completed calls. The current workflow setting supports **MiniMax TTS**; it does not cache native realtime speech-to-speech output.

## Enable caching

1. Select a supported pipeline model configuration with MiniMax as its TTS service. See [Models](/guides/models.md).
2. Open the agent's **Settings → General → Speech Caching**.
3. Enable **Enable Speech Caching** and choose **Save General Settings**.
4. Test repeated phrases with unchanged voice/model settings, inspect the cache metadata, and listen to the generated speech. Publish the draft when ready.

Cached audio has a 24-hour expiry policy and is not a permanent recording. Matching includes the provider request, voice/model settings, output format, and credential identity, within the organization. Similar wording or different synthesis settings need not produce a hit. Expiry, eviction, or invalidation can require synthesis again.

## Inspect the cache

Open **Recordings → TTS cache**. Inspect the phrase preview, provider, model, voice, duration, usage count, and last-used time. Search or sort the list and preview an entry when needed. Preview listening does not increment its synthesis hit count.

Authenticated API access is available under `/api/v1/tts-cache`:

| Operation | Purpose |
| - | - |
| `GET /api/v1/tts-cache` | List the selected organization's entries. Filters include search and duration, with sort by last use, duration, or usage. |
| `GET /api/v1/tts-cache/{entry_id}/audio` | Retrieve a WAV preview. An expired or removed entry returns `404`. |
| `DELETE /api/v1/tts-cache/{entry_id}` | Invalidate one entry. |
| `DELETE /api/v1/tts-cache` | Clear the organization's cache. |

The list supports `offset` and `limit` (1–100, default 25). Use the returned entry ID; it is not a workflow-recording ID. Access uses the selected organization's authenticated session, not a public embed token.

## Invalidate or disable

Remove an entry to stop reusing that cached audio, or clear the organization's cache when appropriate. These actions affect other agents in the same organization that share matching synthesis requests. They do not delete uploaded recordings or completed-call media. A later synthesis can repopulate the cache.

To stop a particular workflow using the feature, turn off **Enable Speech Caching**, save, and publish. Disabling a workflow and clearing stored entries are separate actions.

If the list is empty, check the workflow toggle, MiniMax TTS selection, repeated input/settings, expiry, and organization. `503` indicates the cache is temporarily unavailable; do not interpret it as proof that a voice credential is invalid.


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