Convert text to speech and manipulate audio via APIs and command-line tools.
npx skills add https://github.com/jholhewres/goclaw-skills --skill audio-tts
Please help me install this Agent Skill. Skill: audio-tts Source: https://github.com/jholhewres/goclaw-skills/tree/main/skills/audio-tts Command: npx skills add https://github.com/jholhewres/goclaw-skills --skill audio-tts
This Skill provides a versatile solution for converting text into spoken audio and performing various audio manipulations, streamlining content creation and accessibility.
ffmpeg.Use the audio-tts skill to convert the text "This is a test" into speech using the OpenAI TTS API with the 'alloy' voice.
High-intent search queries and answers about installing and using this skill.
Text to speech conversion is achieved by sending text inputs to APIs like OpenAI, ElevenLabs, Google Cloud TTS, or AWS Polly via curl and processing the returned audio data into playable voiceover files.
Yes, audio files can be transcribed back into text. The Skill supports speech-to-text transcription by leveraging OpenAI's Whisper model to convert spoken audio content into written text.
To manipulate audio files by changing speed, volume, or trimming clips, you need ffmpeg installed, along with curl and jq for handling API interactions and processing JSON outputs.
Yes, this text to speech Skill works with Amazon Polly and Google Cloud TTS. It supports multiple high-quality services, requiring valid API keys to authenticate and generate audio.
The best way to generate a podcast audio version of a blog post is to pass the text into the Skill's text to speech feature, utilizing APIs like OpenAI to create a spoken audio summary.
hasnaGenerate MP3 audio from text using ElevenLabs, OpenAI TTS, or Google Text-to-Speech.
karaage0703Automate podcast episode download, transcription, and summarization from iTunes or RSS feeds.
resemble-aiAutomate AI-narrated Remotion videos with Resemble.ai voiceovers.
MOODMNKY-LLCConverts text to speech offline using sherpa-onnx runtime and voice models.