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

# Voice and speech

> Choose a voice, adjust speech speed, and configure audio settings.

## Voice selection

AssistPulse offers five distinct voices for your agent. Each voice has its own character and tone:

| Voice | Character |
| - | - |
| **Ash** | Neutral and professional |
| **Ballad** | Warm and melodic |
| **Coral** | Friendly and conversational |
| **Sage** | Calm and authoritative |
| **Verse** | Energetic and expressive |

> [!TIP]
>
> The best way to find the right voice is to test each one with a short conversation. Create a test call and listen to how each voice handles your specific instructions.

## Speech speed

Control how fast your agent speaks with the speed slider:

* **0.5×** — slow and deliberate, useful for complex or technical information
* **1.0×** — natural speaking pace (default)
* **2.0×** — fast, suitable for brief confirmations

> [!NOTE]
>
> Speed adjustments apply to the AI's output speech only. Caller speech recognition is not affected.

## Audio settings

> [accordion] Input audio format
>
> The format used for capturing the caller's voice. Options:
>
> * **pcm16** — uncompressed 16-bit PCM (highest quality, default)
> * **g711\_ulaw** — compressed telephony format (lower bandwidth)
> * **g711\_alaw** — alternative telephony compression
>
> For most use cases, the default `pcm16` provides the best recognition accuracy.

> [accordion] Output audio format
>
> The format used for the agent's spoken responses. Same options as input format. Use `pcm16` for best voice quality.

> [accordion] Noise reduction
>
> Reduces background noise from the caller's environment:
>
> * **Near field** — optimized for close-range microphones (headsets, handsets)
> * **Far field** — optimized for speakerphones and distant microphones
> * **Off** — no noise reduction

## Turn detection

Turn detection controls when the agent decides the caller has finished speaking and it's time to respond.

| Setting | Description | Default |
| - | - | - |
| **Silence duration** | How long to wait after the caller stops speaking (ms) | 500ms |
| **Prefix padding** | Audio buffer before voice activity detection (ms) | 300ms |
| **Threshold** | Voice activity detection sensitivity (0-1) | 0.5 |

> [!TIP]
>
> If your agent interrupts callers too often, increase the silence duration to 700-800ms. If it waits too long to respond, decrease it to 300-400ms.

## Transcription

When enabled, every call is transcribed in real time and saved to the call record.

* **Transcription model** — the speech-to-text model used (default: `whisper-1`)
* **Language** — force a specific language for better accuracy, or leave empty for auto-detection

> [!NOTE]
>
> Transcription must be enabled to generate call summaries and sentiment analysis. See [call analysis](https://docs.assist.fm/calls/call-analysis).


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