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

Files1

1 files · 11.1 KB

Select a file to preview

Overall Score

78/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

76

Quality

82

Clarity

79

Completeness

73

Summary

This skill generates TTS audio from a radio show script using the Gemini Interactions API, assigning voices dynamically based on gender tags and applying a simulated telephone bandpass filter to correspondent voices while keeping the host's audio clean. The accompanying Python script orchestrates parallel TTS generation with retries, post-processing via ffmpeg, and WAV concatenation.

Detected Capabilities

file readfile writeshell executionhttp requestapi callexternal command execution (ffmpeg)environment variable read

Trigger Keywords

Phrases that agents use to match this skill to user intent.

radio show ttstelephone effect audiotext to speech voicescorrespondent voice filtermulti-speaker audio generation

Risk Signals

WARNING

Environment variable read: GEMINI_API_KEY

scripts/generate_tts.py:154

INFO

External subprocess execution (ffmpeg) for audio processing

scripts/generate_tts.py:108-119

INFO

Network API calls to Google Gemini service via google-genai SDK

scripts/generate_tts.py:94-106

WARNING

Fallback 'dummy-key' default for GEMINI_API_KEY if unset

scripts/generate_tts.py:154

Referenced Domains

External domains referenced in skill content, detected by static analysis.

www.apache.org

Use Cases

Convert radio show scripts to speech audio with distinct voice effects
Apply telephone filter effects to simulate phone call-in segments
Generate multi-speaker audio with parallel TTS processing
Create radio show content with professional host voice and simulated caller voices
Automate TTS generation with retry logic and dynamic voice assignment

Quality Notes

Strong error handling with retry logic (up to 3 attempts with exponential backoff) for TTS generation failures
Clear voice assignment strategy with dynamic gender-based voice mapping and fallback accent defaults
Well-documented speaker profiles (Paul vs. default caller) with contextual audio direction notes
Comprehensive script parsing supports gender tags ([Male]/[Female]), accent tags ([Accent: ...]), and boost tags
Clear output specification: WAV format, 24kHz, 16-bit PCM, mono with intermediate segments retained for debugging
Good separation of concerns: TTS generation, filtering, and concatenation are independent functions
Parallel processing with ThreadPoolExecutor reduces latency for large scripts
Risk: fallback dummy API key value may cause silent failures if GEMINI_API_KEY is not set in environment
Missing validation: script_path existence is not checked before opening, will raise FileNotFoundError if data/script.md missing
Segments directory creation is idempotent (os.makedirs with exist_ok=True), good defensive practice

Model: claude-haiku-4-5-20251001Analyzed: Oct 29, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

tts-generation