EmpirioLabs AI Speech

Turn text into natural speech with EmpirioLabs AI and save the audio file (MP3, WAV, and other formats). Use when the user asks to read text aloud, create a voiceover, narration, or audio version of a script, or try different voices and languages. Runs a bundled Python script that picks a text-to-speech model from the live catalog (or the one you name) and saves the audio to the path you choose.

EmpirioLabs AI text to speech

Turn text into speech with the EmpirioLabs AI speech API. The bundled script picks a voice model, requests the audio, and saves the file.

Setup

1. Create an API key at https://platform.empiriolabs.ai/dashboard/api-keys. Keys start with sk-empiriolabs-.
2. Make the key available as EMPIRIOLABS_API_KEY in the environment where commands run. Never paste the key into a prompt or a file in the project.
3. Python 3.8 or later. There is nothing to install.

Script paths below are relative to this skill's folder. On Windows, use python instead of python3.

Speak a line of text

bash

python3 scripts/speech.py "Welcome to the weekly product update." --out ./audio/welcome.mp3

The file extension in --out selects the audio format when the model offers it (.mp3, .wav, .ogg, .flac). The script prints a JSON summary:

json

{
  "model": "tts-2",
  "files": ["/home/me/project/audio/welcome.mp3"],
  "urls": ["https://media.empiriolabs.ai/..."]
}

Some models return the audio directly, in which case urls is empty and the saved file is the only copy.

Longer scripts, voices, and languages

bash

python3 scripts/speech.py --text-file ./script.txt --voice Olivia --out ./audio/narration.wav
python3 scripts/speech.py "Bonjour et bienvenue." --language fr-FR --out ./audio/bonjour.mp3
python3 scripts/speech.py --list-voices --model tts-2

Each model has a per-request text limit (for example 2,000 characters). The script stops with a clear message when the text is longer; split long scripts at sentence boundaries and generate one file per part.

Options

Option	Meaning
--model ID	Use a specific model, for example tts-2 or qwen-audio-3-0-tts.
--voice NAME	Voice for the chosen model. See --list-voices.
--language CODE	Language or locale, for example en-US, on models that accept it.
--format FMT	Audio format such as mp3 or wav. Default: taken from --out.
--speed X	Speaking rate on models that accept it (1.0 is normal).
--text-file PATH	Read the text from a UTF-8 file.
--param key=value	Any other model parameter, for example --param temperature=0.8.
--out PATH	File or directory to save to (default: current directory).
--overwrite	Replace an existing file. By default a numeric suffix is added instead.

Choose a model and check prices

bash

python3 scripts/speech.py --list-models

Speech is billed by characters or tokens at the model's listed price. * marks the model used when --model is omitted. For a model's voices, formats, and limits, use the empiriolabs-models skill (models.py --show MODEL_ID).

Exit codes and errors

• 0 success, 1 the request failed (the message says why), 2 invalid arguments or text over the model's limit.
• HTTP 401: the key is missing or invalid. HTTP 402: add credits at https://platform.empiriolabs.ai/dashboard/billing.

Other ways to connect

The same models are available through the EmpirioLabs AI remote MCP server at https://mcp.empiriolabs.ai/mcp (OAuth sign-in, or the API key as a bearer token). Setup: https://docs.empiriolabs.ai/mcp. API reference: https://docs.empiriolabs.ai.