MarkdownTextFilter

Converts Markdown-formatted text to TTS-friendly plain text while preserving structure

Overview

MarkdownTextFilter transforms Markdown-formatted text into plain text that’s suitable for text-to-speech (TTS) systems. It intelligently removes formatting elements while preserving the content structure, including proper spacing and list formatting.

This filter is especially valuable for LLM-generated content, which often includes Markdown formatting that would sound unnatural if read aloud by a TTS system.

Constructor

filter = MarkdownTextFilter(params=InputParams())

params · InputParams

Configuration parameters for the filter

Input Parameters

Configure the filter behavior with these options:

enable_text_filter · bool · default: "True"

Whether the filter is active (when False, text passes through unchanged)

filter_code · bool · default: "False"

Whether to remove code blocks from the output

filter_tables · bool · default: "False"

Whether to remove Markdown tables from the output

filter_repeated_sequences · bool · default: "True"

Whether to remove repeated sequences of 5 or more identical characters from the output

Features

The filter handles these Markdown elements:

• Basic Formatting: Removes *italic*, **bold**, and other formatting markers
• Code: Removes inline code ticks and optionally removes code blocks
• Lists: Preserves numbered lists while removing Markdown formatting
• Tables: Optionally removes Markdown tables
• Repeated Characters: Optionally removes sequences of 5+ repeated characters
• Whitespace: Carefully preserves meaningful whitespace for natural speech
• HTML: Removes HTML tags and converts entities to their plain text equivalents

Usage Examples

Basic Usage with TTS Service

from pipecat.utils.text.markdown_text_filter import MarkdownTextFilter
from pipecat.services.cartesia.tts import CartesiaTTSService

# Create the filter
md_filter = MarkdownTextFilter()

# Use with TTS service
tts = CartesiaTTSService(
    api_key=os.getenv("CARTESIA_API_KEY"),
    voice_id="voice_id_here",
    text_filters=[md_filter]
)

Custom Configuration

# Create filter that removes code blocks and tables
md_filter = MarkdownTextFilter(
    params=MarkdownTextFilter.InputParams(
        filter_code=True,
        filter_tables=True
    )
)

Preserving Repeated Characters

# Keep repeated characters intact (e.g., for phone extension numbers like 22222)
md_filter = MarkdownTextFilter(
    params=MarkdownTextFilter.InputParams(
        filter_repeated_sequences=False
    )
)

What Gets Removed

Markdown Feature	Example	Result
Bold	**important**	important
Italic	*emphasized*	emphasized
Headers	## Section	Section
Code (inline)	`code`	code
Code blocks (when enabled)	```python\ncode\n```
Tables (when enabled)	|A|B|\n|--|--|
HTML tags	<em>text</em>	text
Repeated characters (when enabled)	22222	(removed)

Notes

• Preserves sentence structure and readability
• Maintains whitespace that affects speech prosody
• Handles streaming text with partial Markdown elements
• Efficiently converts HTML entities to plain text characters
• Smart handling of code blocks and tables with state tracking
• Integrates directly with TTS services in the Pipecat pipeline