Skip to content

md_generator.media.audio API Reference

Summary

Item Value
Purpose Convert Audio files to Whisper transcript Markdown
CLI md-audio
Extra audio
Tier medium

Quick CLI reference

Argument Type Required Default Choices Help
input Path required — — Input audio file path
output Path required — — Output .md file path
--model str optional 'base' — Whisper model name (default: base)
--language str optional None — Whisper language (default: auto-detect if omitted). Single code/name (e.g. en, hi) to force, or hi,en / hinglish for Hindi+English mixed (auto-detect + bilingual prompt). Explicit auto / detect is the same as omitting this flag.
--title str optional None — Override document title in Markdown
-v flag optional false — —

Primary symbols

Symbol Kind Notes
DocumentConverter callable —
AudioConverter callable —

Python API (mkdocstrings)

audio

AudioConverter

AudioConverter(*, model_name: str = 'base', language: str | None = None, device: str | None = None)

Bases: DocumentConverter

Transcribe audio with Whisper and attach ffprobe metadata.

AudioMarkdownFormatter

Build Markdown with title, metadata, and timestamped transcript.

AudioToMarkdownService

AudioToMarkdownService(*, converter: AudioConverter | None = None, formatter: AudioMarkdownFormatter | None = None, whisper_model: str = 'base', language: str | None = None)

Transcribe audio and render Markdown using AudioConverter + AudioMarkdownFormatter.

format_timestamped_transcript

format_timestamped_transcript(segments: tuple[TranscriptSegment, ...]) -> str

Format segments as timestamped lines (shared with video module).