elevenlabs-tts

This skill converts text to high-quality audio files using ElevenLabs API. Use this skill when users request text-to-speech generation, audio narration, or voice synthesis with customizable voice parameters (stability, similarity boost) and voice presets (rachel, adam, bella, elli, josh, arnold, ava).

17stars1forksUpdated 2/21/2026

Data Science & ML #voice-synthesis #text-to-speech #audio-generation #elevenlabs-api #python

Security Assessment

Low Risk(80/100)

Detected risks:

Sensitive File Access([SKILL.md] .env)

Security Score80/100

About elevenlabs-tts

The elevenlabs-tts skill provides a powerful solution for converting text into high-quality audio files using ElevenLabs' advanced text-to-speech API. This skill enables users to generate audio narrations or voice synthesis from text input, making it ideal for content creators, developers, and anyone looking to integrate text-to-speech functionality into their applications or workflows. By leveraging ElevenLabs' sophisticated technology, users can ensure clear and natural-sounding voices for their text-based content, improving accessibility and engagement.

FAQ

How do I use the elevenlabs-tts skill to generate speech?

You can generate speech by running the command `python scripts/elevenlabs_tts.py "Your text here"` after ensuring that you have a valid `ELEVENLABS_API_KEY` in your `.env` file. You can also specify a custom voice and output file path.

What are the available voice presets in this skill?

The skill provides seven pre-configured voice presets: `rachel`, `adam`, `bella`, `elli`, `josh`, `arnold`, and `ava`. These voices cover a range of styles from professional to friendly, deep to expressive.

Can I customize the voice parameters?

Yes, you can customize the voice parameters using `stability` and `similarity_boost`. Stability controls the consistency of the voice, while similarity_boost helps to maintain closer adherence to voice characteristics.

What are the output file options?

By default, the output will be saved as `output.mp3`. You can specify a custom file path and name using the `--output` flag, such as `python scripts/elevenlabs_tts.py "Text" --output audio/narration.mp3`.

Do I need any specific environment setup for this skill?

Yes, the skill requires a valid `ELEVENLABS_API_KEY` stored in an `.env` file. Additionally, the script uses `eleven_monolingual_v1` model by default, which can be overridden if necessary.