WaveSpeedAI MiniMax Speech 2.6 TTS

Convert text to speech using MiniMax Speech 2.6 Turbo via WaveSpeed AI. Features ultra-human voice cloning, sub-250ms latency, 40+ languages, emotion control...

Security Scan

The skill's behavior (TTS calls to WaveSpeed) is coherent with its description, but the runtime instructions require an API key and reference an npm package while the registry metadata declares no required credentials or install steps and the source/homepage are unknown — this mismatch is suspicious and should be clarified before use.

Purpose & Capability

The name/description (text-to-speech via MiniMax Speech 2.6) matches the SKILL.md instructions: example code calls wavespeed.run, parameters are TTS-related, and there is no unrelated functionality. However the SKILL.md references an external 'wavespeed' client library (npm) which is not declared in the registry metadata; otherwise capability is coherent.

Instruction Scope

Runtime instructions stay within TTS scope: they show how to set an API key, call the WaveSpeed model, configure voice/emotion/format, and handle errors. The instructions do not ask the agent to read unrelated local files or system secrets beyond the API key, nor do they instruct exfiltration to other endpoints. They do call external network services (the WaveSpeed API), which is expected for a TTS integration.

Install Mechanism

This is an instruction-only skill with no install spec and no code files (low install surface). However, the examples import a 'wavespeed' npm package but the skill does not declare that dependency or provide installation instructions — the author may have assumed the package exists. The lack of a declared install/source for that package and unknown source/homepage increases risk: verify the package origin before running code that imports it.

Credentials

SKILL.md explicitly instructs users to set WAVESPEED_API_KEY, but the registry metadata lists no required environment variables and no primary credential. This mismatch means the skill silently requires a secret to function even though metadata doesn't declare it. The requested secret (an API key for the external TTS service) is plausible for the skill's purpose, but the missing declaration and unknown publisher/homepage are concerning and should be corrected or explained.

Persistence & Privilege

The skill does not request always:true, does not modify system or other skills, and is instruction-only so it does not install persistent components. Default autonomous invocation is allowed (normal for skills) but there are no indications of privileged persistence.

What to consider before installing

Before installing or using this skill: (1) Confirm the publisher and the legitimacy of wavespeed.ai (or the package author) — the registry metadata has no homepage/source. (2) Ask the publisher to update metadata to declare the required WAVESPEED_API_KEY and any package dependencies, so you know what secrets/dependencies are needed. (3) Inspect or verify the 'wavespeed' npm package (or other client) on the official registry and prefer installing from the official package name and a trusted source. (4) If you must provide an API key, consider creating a limited-scope/test key, not a long-lived production key, and avoid sending sensitive PII through the service. (5) Run in an isolated environment or sandbox first and monitor network calls. (6) If the publisher cannot explain the metadata mismatch or provide a trustworthy source, treat the skill as untrusted.

WaveSpeedAI MiniMax Speech 2.6 Turbo

Convert text to speech using MiniMax Speech 2.6 Turbo via the WaveSpeed AI platform. Features ultra-human voice cloning, sub-250ms latency, 40+ language support, and emotion control.

Authentication

export WAVESPEED_API_KEY="your-api-key"

Get your API key at wavespeed.ai/accesskey.

Quick Start

import wavespeed from 'wavespeed';

const output_url = (await wavespeed.run(
  "minimax/speech-2.6-turbo",
  {
    text: "Hello, welcome to WaveSpeed AI!",
    voice_id: "English_CalmWoman"
  }
))["outputs"][0];

API Endpoint

Model ID: minimax/speech-2.6-turbo

Convert text to speech with configurable voice, emotion, speed, pitch, and audio format.

Parameters

Parameter	Type	Required	Default	Description
text	string	Yes	--	Text to convert to speech. Max 10,000 characters. Use <#x#> between words to insert pauses (0.01-99.99 seconds).
voice_id	string	Yes	--	Voice preset ID. See Voice IDs below.
speed	number	No	1	Speech speed. Range: 0.50-2.00
volume	number	No	1	Speech volume. Range: 0.10-10.00
pitch	number	No	0	Speech pitch. Range: -12 to 12
emotion	string	No	happy	Emotional tone. One of: happy, sad, angry, fearful, disgusted, surprised, neutral
english_normalization	boolean	No	false	Improve English number reading normalization
sample_rate	integer	No	--	Sample rate in Hz. One of: 8000, 16000, 22050, 24000, 32000, 44100
bitrate	integer	No	--	Bitrate in bps. One of: 32000, 64000, 128000, 256000
channel	string	No	--	Audio channels. 1 (mono) or 2 (stereo)
format	string	No	--	Output format. One of: mp3, wav, pcm, flac
language_boost	string	No	--	Enhance recognition for a specific language. See Supported Languages.

Example

import wavespeed from 'wavespeed';

const output_url = (await wavespeed.run(
  "minimax/speech-2.6-turbo",
  {
    text: "The quick brown fox jumps over the lazy dog.",
    voice_id: "English_expressive_narrator",
    speed: 1.0,
    pitch: 0,
    emotion: "neutral",
    format: "mp3",
    sample_rate: 24000,
    bitrate: 128000
  }
))["outputs"][0];

Pause Control

Insert pauses in speech using <#x#> syntax where x is seconds (0.01-99.99):

const output_url = (await wavespeed.run(
  "minimax/speech-2.6-turbo",
  {
    text: "And the winner is <#2.0#> WaveSpeed AI!",
    voice_id: "English_CaptivatingStoryteller"
  }
))["outputs"][0];

Advanced Usage

Sync Mode

const output_url = (await wavespeed.run(
  "minimax/speech-2.6-turbo",
  {
    text: "Hello world!",
    voice_id: "English_CalmWoman"
  },
  { enableSyncMode: true }
))["outputs"][0];

Custom Client with Retry Configuration

import { Client } from 'wavespeed';

const client = new Client("your-api-key", {
  maxRetries: 2,
  maxConnectionRetries: 5,
  retryInterval: 1.0,
});

const output_url = (await client.run(
  "minimax/speech-2.6-turbo",
  {
    text: "Welcome to our platform.",
    voice_id: "English_Trustworth_Man"
  }
))["outputs"][0];

Error Handling with runNoThrow

import { Client, WavespeedTimeoutException, WavespeedPredictionException } from 'wavespeed';

const client = new Client();
const result = await client.runNoThrow(
  "minimax/speech-2.6-turbo",
  {
    text: "Testing speech generation.",
    voice_id: "English_CalmWoman"
  }
);

if (result.outputs) {
  console.log("Audio URL:", result.outputs[0]);
  console.log("Task ID:", result.detail.taskId);
} else {
  console.log("Failed:", result.detail.error.message);
  if (result.detail.error instanceof WavespeedTimeoutException) {
    console.log("Request timed out - try increasing timeout");
  } else if (result.detail.error instanceof WavespeedPredictionException) {
    console.log("Prediction failed");
  }
}

Voice IDs

English Voices (Popular)

Voice ID	Description
English_CalmWoman	Calm female voice
English_Trustworth_Man	Trustworthy male voice
English_expressive_narrator	Expressive narrator
English_radiant_girl	Radiant girl voice
English_magnetic_voiced_man	Magnetic male voice
English_CaptivatingStoryteller	Storyteller voice
English_Upbeat_Woman	Upbeat female voice
English_GentleTeacher	Gentle teacher voice
English_PlayfulGirl	Playful girl voice
English_ManWithDeepVoice	Deep male voice
English_ConfidentWoman	Confident female voice
English_Comedian	Comedic voice
English_SereneWoman	Serene female voice
English_WiseScholar	Scholarly voice
English_Cute_Girl	Cute girl voice
English_Sharp_Commentator	Sharp commentator
English_Lucky_Robot	Robot voice

General Voices

Wise_Woman, Friendly_Person, Inspirational_girl, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Patient_Man, Young_Knight, Determined_Man, Lovely_Girl, Decent_Boy, Imposing_Manner, Elegant_Man, Abbess, Sweet_Girl_2, Exuberant_Girl

Special Voices

whisper_man, whisper_woman_1, angry_pirate_1, massive_kind_troll, movie_trailer_deep, peace_and_ease

Other Languages

Voices are available for: Chinese (Mandarin), Cantonese, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans.

Voice IDs follow the pattern {Language}_{VoiceName} (e.g., Japanese_KindLady, Korean_SweetGirl, French_CasualMan).

Supported Languages

For language_boost: Chinese, Chinese,Yue, English, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans

Pricing

$0.06 per 1,000 characters.

Security Constraints

• API key security: Store your WAVESPEED_API_KEY securely. Do not hardcode it in source files or commit it to version control. Use environment variables or secret management systems.
• Input validation: Only pass parameters documented above. Validate text content before sending requests.