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

# Transcriber

> Used to configure your speech recognition.

## Overview

Transcription is one of the key elements of a conversation; Vocode allows
developers to configure their transcription to suit their use case.

## TranscriberConfig Class

The base `TranscriberConfig` class defines several key fields that all
transcriber implementations use.

<ParamField path="sampling_rate" type="int" required={true}>
  The sampling rate of the audio to be transcribed.
</ParamField>

<ParamField path="audio_encoding" type="AudioEncoding" required={true}>
  The encoding format of the audio to be transcribed.
</ParamField>

<ParamField path="chunk_size" type="int" required={true}>
  The size of the audio chunks to be transcribed.
</ParamField>

<ParamField path="endpointing_config" type="Optional[EndpointingConfig]" required={false}>
  An optional configuration for which endpointing implementation to use.
</ParamField>

## Transcriber Implementations

### DeepgramTranscriberConfig

<ParamField path="model" type="Optional[str]" required={false}>
  Specifies which Deepgram model to use for transcription.
</ParamField>

<ParamField path="should_warmup_model" type="bool" required={false}>
  Whether to warm up the model before starting transcription.
</ParamField>

<ParamField path="version" type="Optional[str]" required={false}>
  The version of the Deepgram transcription API to use. If not specified, the
  latest version will be used.
</ParamField>

### GoogleTranscriberConfig

<ParamField path="model" type="Optional[str]" required={false}>
  Specifies which Google model to use for transcription.
</ParamField>

<ParamField path="should_warmup_model" type="bool" required={false}>
  Whether to warm up the model before starting transcription.
</ParamField>

### AssemblyAITranscriberConfig

<ParamField path="should_warmup_model" type="bool" required={false}>
  Whether to warm up the model before starting transcription.
</ParamField>