# STT Settings

Use the `stt` object in an [Advanced Settings](/docs/advanced-settings) resource to bias recognition toward specific words and tune transcript finalisation after silence.

## Overview

With supported providers, `keyterms` helps recognise names and domain-specific vocabulary. `endpointing` controls how long the transcription engine waits after silence before finalising a transcript.

STT settings work alongside [VAD Settings](/docs/vad-settings) and the turn detector. Transcript finalisation and end-of-turn detection run together, and the platform can start generating a response before the turn is committed. Provider buffering, turn detection and response generation all affect when the caller hears a reply; the two configured delays are not a complete latency formula.

:::info{title="Note"}

STS (Speech-to-Speech) models consume audio directly and have no separate transcription step, so `endpointing` does not apply to them. `keyterms` still applies, through a different mechanism. See [STT settings with STS models](#stt-settings-with-sts-models) below.

:::

## Data model

Both fields are optional. Omit `keyterms` to use an empty list. Omit `endpointing` or set it to `null` to use the integration default.

| Field         | Type           | Default                   | Description                                           |
| ------------- | -------------- | ------------------------- | ----------------------------------------------------- |
| `keyterms`    | string[]       | `[]`                      | Individual words the STT engine should prioritise     |
| `endpointing` | number \| null | `null` (integration default) | Seconds of silence before the transcript is finalised |

**Example:**

```json
{
  "stt": {
    "keyterms": ["Reecall", "ACME"],
    "endpointing": 0.5
  }
}
```

***

## Provider support

Not every STT provider supports every setting. For `endpointing: null`, the platform uses the integration defaults below. These values are sent by the integration and may differ from the provider's native defaults.

| Model                                | `keyterms` | `endpointing`           | ID                                     |
| ------------------------------------ | ---------- | ----------------------- | -------------------------------------- |
| Deepgram Nova-3                      | Yes        | Yes (default: `0.025`s) | `0dda8a0b-5a55-42dc-9071-88b75bff5d78` |
| Deepgram Nova-2                      | Yes        | Yes (default: `0.025`s) | `7a67c6a2-c2a1-40ae-ad78-720552cf2482` |
| AssemblyAI Universal-3.5 Pro Realtime | Yes       | Yes (default: `0.1`s)   | `a7c3e9f1-4b2d-4e8c-9a5f-1d7b3e6c2a01` |
| Gladia Solaria-1                     | Yes        | Yes (default: `0.05`s)  | `56510288-e114-4bed-9357-3fb57188a54c` |
| Speechmatics Standard                | Yes        | Yes (default: `0.5`s)   | `f5b82a3d-9c4e-4d0f-b2a6-7e3f9c5d8b01` |
| Speechmatics Enhanced                | Yes        | Yes (default: `0.5`s)   | `f5b82a3d-9c4e-4d0f-b2a6-7e3f9c5d8b02` |
| Voxtral Mini Transcribe Realtime     | Yes        | No                      | `600592b5-54d1-4bc4-a8ab-770c376b235f` |
| Voxtral Mini Transcribe 2            | Yes        | No                      | `3da23fc4-ffd8-4e19-8145-e788317ca27c` |
| GPT Realtime 2.1                     | Yes        | No                      | `e5a9c8d6-0f7b-4e2c-9d0a-6b2f4c0e7d08` |
| GPT Realtime 2.1 Mini                | Yes        | No                      | `f6b0d9e7-1a8c-4f3d-8e1b-7c3a5d1f8e09` |
| GPT Realtime 2                       | Yes        | No                      | `b3d34d2a-8254-405a-8704-4108b2f097d7` |
| GPT Realtime 1.5                     | Yes        | No                      | `b1d67e16-b522-49f4-88e9-6f0acac76dbb` |

For Deepgram Flux, `endpointing` is mapped to `eot_timeout_ms` and clamped to 0.5 to 60 seconds. The Cartesia, Gradium and Voxist integrations do not apply these STT tuning fields. LiveKit inference does not receive the configured `endpointing`; its support for session keyterms depends on the underlying model.

The GPT Realtime entries are STS models rather than transcription engines. They accept `keyterms` through the mechanism described below, and never `endpointing`.

***

## STT Settings with STS models

An STS model receives audio and produces audio without a separate transcription step, which changes how the two `stt` fields behave.

`endpointing` has no effect on STS models. Use the supported `vad` fields to configure turn-taking. See [VAD with STS models](/docs/vad-settings#vad-with-sts-models) for provider support.

`keyterms` is added to an STS Assistant's instructions as a dedicated section. It tells the model that these terms may appear and to spell them exactly as written. A separate transcription engine instead receives keyterms as recognition hints.

The effect of instruction-based keyterms depends on the STS model. Use the spellings you want the Assistant to produce. Recognition is not guaranteed.

:::info{title="Note"}

Keyterms use prompt space on an STS model. Include terms that are often misheard instead of the full product catalogue.

:::

***

## Configuring STT properties

### `keyterms`

List words the STT engine should prioritise during recognition, such as proper nouns, brand names, product names, or domain-specific vocabulary. Multi-word phrases are accepted by the API; support depends on the provider. The Voxtral integration splits entries on whitespace and commas into individual tokens.

```json
{
  "stt": {
    "keyterms": ["Reecall", "ACME"]
  }
}
```

Provide the spelling you want the recogniser to favour. For example, add `"Reecall"` if it is often transcribed as `"recall"`. Keyterms are hints and do not guarantee a particular transcription.

Keyterms are capped at 100 entries and 100 characters per entry. Empty or whitespace-only strings are rejected.

***

### `endpointing`

Controls how long (in seconds) the STT engine waits after detecting silence before finalising the transcript. This is a separate silence timer from the VAD's `endpointingMinDelay`: VAD decides when the user's turn ends at the audio level, while `endpointing` determines when the STT engine commits its transcript.

```json
{
  "stt": {
    "endpointing": 0.5
  }
}
```

The STT engine and turn detector both affect response timing, but buffering, adaptive endpointing and preemptive generation mean the audible delay cannot be calculated as the maximum of these two settings. Test both controls with representative calls.

* **Lower values** (`0.2` to `0.4`): the Assistant responds faster but may cut off users who pause mid-sentence.
* **Higher values** (`0.6` to `1.0`): the Assistant gives the user more time to continue speaking but adds latency before responding.

When set to `null`, the Assistant uses the integration's default endpointing value (see the Provider Support table above for provider-specific defaults). On an STS model the field has no effect at all, whatever its value.

Minimum value is `0`, expressed in seconds. Typical range: `0.2` to `1.0`.

## What's next

- [Advanced Settings](/docs/advanced-settings)
- [VAD Settings](/docs/vad-settings)
- [Sounds Settings](/docs/sounds-settings)
