Transcribe audio to text with Whisper and synthesize speech with 11Labs.
npx skills add https://github.com/bishwashere/cowCode --skill speech-bishwashere
Please help me install this Agent Skill. Skill: Speech Source: https://github.com/bishwashere/cowCode/tree/main/skills/speech Command: npx skills add https://github.com/bishwashere/cowCode --skill speech-bishwashere
Transcribe audio content into text for easy search, note-taking, and archiving, and convert text into natural-sounding speech to respond or narrate content.
To begin, provide an audio file to transcribe or supply text to synthesize; the skill will perform transcription or speech synthesis accordingly.
High-intent search queries and answers about installing and using this skill.
To transcribe audio to text, provide your audio file and the skill uses Whisper to generate accurate transcripts for meetings, voice notes, and archiving.
To generate spoken audio from text, supply your text and the skill uses 11Labs synthesis to create natural-sounding speech with configurable voice and language options.
Yes, you can use 11Labs speech synthesis to generate spoken audio replies within chats, enabling you to narrate content or respond in spoken form alongside transcribing audio.
Whisper transcription processes audio into searchable text, and the skill provides configurable language and output options to handle various transcription and synthesis workflows.
You need audio processing for accessibility workflows when converting audio into text for screen readers, or generating spoken audio from text to assist users requiring voice-based content delivery.
SpillwaveSolutionsTranscribe audio and video to text using Whisper with markdown context grounding.
managedcodeConvert office and rich-text documents to Markdown for .NET applications.
MaTriXyGenerate spoken replies on-device using local TTS from URLs or chat prompts.
nuno7lopesConvert text input to spoken audio using ElevenLabs text-to-speech.
