Speech & Transcription

This skill provides high-quality voice synthesis with multiple personas.

This skill aims to give the AI agent a voice.

Provides a reference for Hebrew vowel points (nikud) for AI agents.

This skill allows the AI to generate audio responses using text-to-speech technology.

This skill generates speech audio using the Deepdub service.

This skill uses the SiliconFlow API to generate speech from text.

This skill is designed to generate audio content like audiobooks, podcasts, or educational audio.

This skill uses ElevenLabs text-to-speech technology to provide a Mac-style 'say' user experience.

This skill provides integration for ElevenLabs Text-to-Speech, a service for generating speech from text.

This skill helps you generate draft articles and outlines.

This skill aims to provide a metallic AI voice persona with text-to-speech and visual transcript styling.

This skill uses the Doubao Text-to-Speech service from Volcano Engine to convert text into speech.

This skill uses AssemblyAI to transcribe audio or video files.

This skill helps refine text by removing AI-generated jargon and making it sound more human.