Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Fixed typo in file names: renamed "resemble-stt.md" and "resemble-tts.md" to "ressemble-stt.md" and "ressemble-tts.md" - Added new script files: scripts/stt.sh and scripts/tts.sh for easier command-line usage
What This Skill Does
Connects to the Resemble AI HTTP API to convert text into speech and transcribe audio files to text. TTS returns MP3 audio as base64; STT uploads audio and polls until the transcript is ready.
Async polling is handled automatically, so the agent waits for transcription to finish without requiring manual status checks.
When to use it
- Generating voiceovers for video scripts
- Transcribing recorded meetings or interviews
- Adding spoken narration to automated reports
- Converting chatbot replies to audio
- Prototyping voice-enabled app features
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Transcribe this audio file and return the text
- 1Uploads the audio file to Resemble AI via multipart request
- 2Receives a transcription job ID from the API
- 3Polls the API at intervals until the job status is complete
- 4Extracts and returns the clean transcript text
Plain text transcript of the audio file
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.