Generate natural text-to-speech audio via the ElevenLabs TTS API.
npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill sag-moodmnky-llc
Please help me install this Agent Skill. Skill: sag Source: https://github.com/MOODMNKY-LLC/mnky-atlas/tree/main/skills/sag Command: npx skills add https://github.com/MOODMNKY-LLC/mnky-atlas --skill sag-moodmnky-llc
This Skill eliminates the friction of generating high-quality text-to-speech audio, removing the need to navigate clunky web-based TTS platforms or manually configure complex audio settings for natural-sounding speech output.
eleven_v3, stable eleven_multilingual_v2, and fast eleven_flash_v2_5 voice models to balance quality, speed, and stability for different use cases.[whispers], [short pause], and [excited] to adjust tone, pacing, and emotion for context-aware, natural speech.Use the sag skill to generate a natural-sounding text-to-speech audio file of your input text with your preferred voice and delivery style.
High-intent search queries and answers about installing and using this skill.
To generate natural text-to-speech audio, the Skill processes your input text using the ElevenLabs TTS API. It accesses multiple voice models and applies custom delivery tags to produce high-quality voiceover files.
Yes, a valid ElevenLabs API key is required for text-to-speech voice generation. You also need the sag CLI tool installed locally to access voice models, custom delivery tags, and local audio playback.
Yes, you can control tone and pacing in speech synthesis by applying built-in audio delivery tags. Use tags like [whispers], [short pause], and [excited] within your input text to adjust emotion and pacing.
Available ElevenLabs voice models for text-to-speech conversion include the expressive eleven_v3, the stable eleven_multilingual_v2, and the fast eleven_flash_v2_5. These options let you balance quality, speed, and stability.
The best way to create a voiceover without manual configuration is using a CLI-driven TTS Skill. It eliminates clunky web platforms by directly sending your text and delivery tags to the ElevenLabs API to generate speech.
You should use the eleven_flash_v2_5 model over eleven_v3 for speech synthesis when fast generation speed is prioritized over expressive delivery. Conversely, choose eleven_v3 when maximum expressiveness and natural tone are required.
RachasumanthConvert text to speech via the ElevenLabs API with local playback.
hoanghd218Convert video scripts into MP3 voiceover audio via the MiniMax TTS API.
matt-fell-aiDispatch text-to-speech to an external provider via a speak function and CLI.
TikTzukiConvert text to speech and transcribe audio via cloud APIs.