Telnyx Tts

Generate speech audio from text using Telnyx Text-to-Speech API. Use when you need to convert text to spoken audio, create voice messages, or generate audio content.

Security Scan

The skill's code, instructions, and requested environment variable align with its stated Telnyx TTS purpose; nothing in the files suggests hidden exfiltration or unrelated access, though a missing Python dependency note and standard API-key cautions apply.

Purpose & Capability

Name/description match the code and runtime instructions. The script connects to Telnyx's TTS WebSocket endpoint and uses TELNYX_API_KEY for authentication — exactly what a Telnyx TTS helper would need.

Instruction Scope

SKILL.md simply instructs running the included Python CLI to produce an audio file and return it; the instructions do not request unrelated files or secrets. Note: the CLI sends the provided text and API key to Telnyx (expected for TTS).

Install Mechanism

No install spec (instruction-only) — low risk. However, the script requires the Python 'websockets' package but the skill metadata only declares the 'python3' binary; the missing declared dependency may cause runtime errors and should be noted.

Credentials

Only TELNYX_API_KEY is requested and it is necessary for the Telnyx API. Consider that this key grants actions on your Telnyx account (usage/billing); limit scope or use a key with minimal privileges where possible.

Persistence & Privilege

The skill is not always-enabled and does not request persistent or system-wide changes. It does not modify other skills or access unrelated config paths.

Assessment

This skill appears to do exactly what it claims: send text to Telnyx and write back audio. Before installing, confirm you trust the skill source and are comfortable exposing a TELNYX_API_KEY (it can incur usage/billing). Install the Python 'websockets' dependency (pip install websockets) in a controlled environment, or run the script in a sandbox. Prefer using a Telnyx API key with limited permissions or usage limits and rotate the key after testing. If you need higher assurance, review the included script yourself or run it with a test account to verify behavior.

Telnyx Text-to-Speech

Generate high-quality speech audio from text using the Telnyx TTS API.

Usage

To convert text to speech, run the script:

{baseDir}/scripts/telnyx-tts.py "Your text here" -o /tmp/output.mp3

The script outputs the path to the generated audio file on success.

Options

• -o, --output PATH: Output file path (default: output.mp3)
• --voice VOICE: Voice ID (default: Telnyx.NaturalHD.astra)

Available Voices

Telnyx provides multiple voice options:

• Telnyx NaturalHD: Premium voices with refined prosody
  • Telnyx.NaturalHD.astra (default)
  • Telnyx.NaturalHD.luna
  • Telnyx.NaturalHD.andersen_johan
• Telnyx KokoroTTS: Budget-friendly for high-volume
  • Telnyx.KokoroTTS.af
  • Telnyx.KokoroTTS.am

Example

Generate speech and return as media:

{baseDir}/scripts/telnyx-tts.py "Hello! This is a test of Telnyx text to speech." -o /tmp/tts-output.mp3

Then return the audio file:

MEDIA: /tmp/tts-output.mp3

For Telegram voice notes, the audio will be sent as a voice message.

Environment

Requires TELNYX_API_KEY environment variable to be set.