Convert text to speech and transcribe audio with multiple providers.
npx skills add https://github.com/zeenie-ai/OpenCompany --skill speech-skill
Please help me install this Agent Skill. Skill: speech-skill Source: https://github.com/zeenie-ai/OpenCompany/tree/main/server/skills/language_agent/speech-skill Command: npx skills add https://github.com/zeenie-ai/OpenCompany --skill speech-skill
This Skill removes the friction of building voice-enabled workflows by letting you convert text to spoken audio and transcribe spoken audio back into text with a single, reusable interface.
Connect the speech skill to your workflow and configure the provider credential, then send it either text for synthesis or an audio file for transcription.
High-intent search queries and answers about installing and using this skill.
To convert text to speech for agent voice loops, this Skill synthesizes playable spoken audio from text inputs, enabling automated narration, voiceovers, and spoken agent responses within your configured workflows.
Yes, you can transcribe audio files with diarization and timestamps. This Skill processes spoken audio references into text, supporting language hints, speaker diarization, and timestamp generation for downstream analysis.
Yes, you need provider-specific credentials to use text to speech and speech to text. This Skill requires valid API keys for your chosen provider, such as OpenAI, ElevenLabs, Deepgram, Groq, or Sarvam AI.
To choose between ElevenLabs, Deepgram, and Groq for audio transcription, compare provider capabilities based on your specific quality, latency, language, and speaker diarization needs for your workflow.
To build a voice loop that listens to a recording and speaks back a response, connect this Skill to your workflow, transcribe the upstream audio reference to text, reason over the transcript, and synthesize an audio reply.
jx1100370217Configure local TTS and STT voice capabilities for OpenClaw.
michaelboedingConvert text into speech using Gemini, ElevenLabs, or OpenAI TTS backends.
reedmayhew18Transcribe voice chat messages with Whisper and route text downstream.
kaivyyTranscribe audio files with OpenAI Whisper and synthesize speech from text.
