zvukogram
par erview
Search & ResearchRésumé
Text-to-Speech via Zvukogram API with SSML support.
Description
Ce que fait ce skill
Generates speech from text using the Zvukogram API. Supports SSML markup for stress marks, pauses, and speed control. Can merge multiple audio fragments and handle English word transcription for Russian TTS.
SSML support with per-word stress control and English transcription aliases gives more accurate Russian-language output than basic TTS APIs.
Quand l'utiliser
- Converting written articles to audio files
- Adding voice notifications to automated pipelines
- Recording podcast narration with multiple voices
- Voicing news scripts with proper pronunciation control
- Generating audio from long-form text documents
Exemple de workflow
User asks: 'Read this news summary aloud with a pause after the headline, using a female voice'
- 1
Wraps headline in SSML with a <break time='500ms'/> after it
- 2
Adds <sub alias='...'/> tags for any English brand names in the text
- 3
Calls tts.py with --voice Алена and the SSML-formatted text
- 4
Saves output to a local .mp3 file
An .mp3 file with the news summary spoken by Алена, pausing after the headline and pronouncing brand names correctly
Prérequis
- ZVUKOGRAM_TOKEN environment variable (obtain at https://zvukogram.com/)
- ZVUKOGRAM_EMAIL environment variable (your Zvukogram account email)
Installation
clawhub install erview/zvukogramExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.