Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Bots can hear too — STT/transcription featured prominently alongside TTS
What This Skill Does
Text-to-speech and speech-to-text access via the ScrappyLabs API, built for autonomous agents. Agents self-register through the API without human account creation, receiving a bearer token and character allowance. Supports 20+ preset voices, custom voice design from text descriptions, and audio transcription in multiple formats.
Agents can register and obtain API credentials autonomously without any human signup, unlike most TTS services that gate access behind account creation.
When to use it
- Adding spoken narration to automated status reports
- Transcribing voice messages in a chatbot pipeline
- Giving an agent a distinct voice for audio alerts
- Designing a custom voice persona for a branded assistant
- Converting recorded audio files to text for downstream processing
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Give my agent a voice and say 'Hello, I am online.'
- 1Call GET /v1/molt/discover to confirm availability and list voices
- 2POST to /v1/molt/initiate with a bot_id and bot_name to receive a bearer token and 5,000 free characters
- 3POST to /v1/audio/speech with the token, chosen voice, and input text
- 4Receive and save the returned MP3 file
MP3 file of the agent speaking 'Hello, I am online.' in the selected voice
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.