Exposes a 100% local, offline PDF batch extraction utility (extract_to_markdown.py) that isolates invoices under invoices/ and translates PDFs into clean Markdown files for LLM-native parsing.

2026-05-1648

reconciliation

google-gemini/gemini-managed-agents-templates

Reconcile loaded expenses against the pre-parsed invoice database, flagging discrepancies like amount mismatches, missing invoices, and merchant mismatches locally.

2026-05-1648

name	tts-generation
description	Convert radio show script to speech audio with telephone effect on correspondent voices using the Interactions API.

TTS Generation

Convert the radio show script into speech audio using the Gemini TTS model via the Interactions API. Apply a telephone bandpass filter to correspondent voices so they sound like phone call-ins, while keeping the host's voice clean studio-quality.

Embedded Script

python3 skills/tts-generation/scripts/generate_tts.py --workspace ./workspace

Arguments

Argument	Default	Description
`--workspace`	`workspace`	Root workspace directory
`--workers`	`8`	Max parallel TTS worker threads

What it does

Reads the script from {workspace}/data/script.md.
Parses it into individual (speaker, text) turns and assigns voices.
Generates TTS for all turns in parallel using a thread pool (default 8 workers).
Retries each failed turn up to 3 times with exponential backoff.
Applies an ffmpeg telephone bandpass filter (300Hz–3.4kHz) to correspondent voices.
Keeps the host (Paul) audio clean and unfiltered.
Concatenates all segments in original script order into a single WAV.

Dependencies

google-genai (>= 2.0.0)
ffmpeg (system)

API Details

Uses the Interactions API with single-speaker TTS — no multi-speaker workaround needed.

Voice Assignment

Voices are assigned dynamically based on [Male] / [Female] gender tags in the script:

Speaker	Voice	Audio Treatment
Paul (host)	`Puck`	Clean — no filter
Caller `[Female]` — 1st	`Kore`	Telephone filter
Caller `[Female]` — 2nd	`Aoede`	Telephone filter
Caller `[Male]` — 1st	`Charon`	Telephone filter
Caller `[Male]` — 2nd	`Fenrir`	Telephone filter

Voices cycle round-robin if there are more callers than available voices. Accent tags ([Accent: Irish], etc.) are injected into the TTS prompt to influence pronunciation.

Telephone Filter

Applied via ffmpeg to correspondent audio segments:

highpass=f=300, lowpass=f=3400, acompressor, volume=1.5

This simulates the standard telephone bandwidth (300Hz–3.4kHz) and adds compression to mimic phone codec dynamics.

Output

Primary output: {workspace}/audio/speech/speech.wav
Format: WAV, 24kHz, 16-bit PCM, mono
Intermediate segments: {workspace}/audio/speech/segments/turn_*.wav