ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified media Safety 4/5

telnyx-stt

Transcribe audio files to text using Telnyx Speech-to-Text API. Use when you need to convert audio recordings, voice messages, or spoken content to text.

Why use this skill?

Efficiently transcribe audio files like MP3, WAV, and OGG to text using the powerful Telnyx Speech-to-Text API within OpenClaw. Easy installation and usage.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/dotcom-squad/telnyx-stt
Or

What This Skill Does

The telnyx-stt skill is a robust transcription tool integrated into the OpenClaw agent ecosystem. Powered by the Telnyx Speech-to-Text API and the sophisticated Whisper model, this skill converts a wide array of audio file formats into accurate, machine-readable text. Whether you are dealing with recorded voice memos, meeting transcripts, or audio snippets from web sources, this skill automates the labor-intensive process of manual transcription, allowing your agent to process spoken data with high fidelity and efficiency.

Installation

To integrate this capability into your OpenClaw environment, execute the following command in your terminal:

clawhub install openclaw/skills/skills/dotcom-squad/telnyx-stt

Ensure that you have an active Telnyx account and your API credentials available. Before running the skill, you must export your API key into your system environment by running export TELNYX_API_KEY='your_api_key_here'. Failure to provide this variable will result in an authentication error.

Use Cases

  • Meeting Summarization: Convert recorded audio from team syncs into text logs for documentation.
  • Voice Note Processing: Transcribe voice messages captured in the field into actionable task lists or notes.
  • Content Accessibility: Generate transcriptions for audio-only media, making content searchable and accessible to users with hearing impairments.
  • Research: Process long-form audio interviews or focus group recordings into structured text for data analysis.

Example Prompts

  1. "Transcribe the audio file located at /home/user/downloads/interview_01.mp3 and summarize the main action items."
  2. "Listen to the file /tmp/voice_note.ogg and save the full transcription into a text file named notes.txt."
  3. "Convert the provided voice recording at /mnt/data/call_log.wav into text so I can review what was discussed."

Tips & Limitations

  • Supported Formats: The skill supports standard formats including MP3, WAV, OGG, M4A, and WebM. Ensure your file extension matches the actual encoding.
  • API Costs: Be aware that Telnyx charges per minute of audio processed. Monitor your usage to avoid unexpected billing.
  • Privacy: As this skill uses an external API, do not upload sensitive or classified audio recordings that violate your organization's data compliance policies.

Metadata

Stars1335
Views0
Updated2026-02-23
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-dotcom-squad-telnyx-stt": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#transcription#audio#whisper#speech-to-text#voice
Safety Score: 4/5

Flags: file-read, external-api, code-execution