设计与多媒体

text to speech / tts unlimitedtts.com x402

试用

Create text-to-speech narration and MP3 audio with UnlimitedTTS using x402 USDC payments. Use for text-to-speech, narration, read-aloud, voice generation, MP3 creation, UnlimitedTTS, or wallet-paid/x402 speech requests.

它能做什么

Create text-to-speech narration and MP3 audio with UnlimitedTTS using x402 USDC payments. Use for text-to-speech, narration, read-aloud, voice generation, MP3 creation, UnlimitedTTS, or wallet-paid/x402 speech requests.

技能文档

UnlimitedTTS

Create paid speech without handling wallet secrets. Prefer the UnlimitedTTS MCP tools. Use direct HTTP only when those tools are unavailable and a conforming x402 wallet-aware HTTP client is already present.

MCP workflow

  1. Call tts_list_voices when the voice is missing, ambiguous, or rejected. Use the full provider-prefixed id such as openai_nova.
  2. Call tts_quote with the exact text, voice, speed, and any user-stated maxUsdc.
  3. Check the exact amount, expiry, policy result, and user budget before signing.
  4. When an external wallet tool is required, ask it to sign only selectedRequirement from this quote. Never request or expose a seed phrase, private key, or secret.
  5. Call tts_synthesize once with the unchanged text, voice, speed, quote token, and returned paymentSignature.
  6. Require payment.settled: true. Return or send the MP3 attachment/resource, not base64.

Treat tts_synthesize as irreversible and not replay-safe. Never retry PAYMENT_OUTCOME_UNKNOWN; inspect the wallet or settlement receipt and ask the user before any new quote or authorization.

Character limits vary by voice. If the text exceeds the character limit, split it into multiple chunks and call tts_synthesize for each chunk. Each chunk is a separate paid request. Get approval for the aggregate plan before proceeding.

Direct HTTP mode

Read direct-x402.md only when MCP tools are unavailable and the agent already has both HTTP and x402 signing capability.

Read errors.md when a tool or API call fails.

相关技能

Minimax Tts

MiniMax Text-to-Speech synthesis using the HTTP REST API. Generates high-quality audio from text in 40+ languages with ultra-realistic voices. Use when the u...

1 次安装

OATDA Generate Speech

Generate speech or audio from text using OATDA's unified audio API. Triggers when the user wants to convert text to speech, create narration, voiceovers, acc...

14 次安装

Speak

把任意文本改写成可直接喂给 TTS 引擎的朗读稿，处理数字、单位、缩写、URL 与发音。

58 次安装2 星标

qwenspeak

Text-to-speech generation via Qwen3-TTS over SSH. Preset voices, voice cloning, voice design. Use when the user wants to generate speech audio, clone voices, or work with TTS.

55 次安装

Voiceover

Generate spoken voiceover and narration from a script, one speaker, with control over emotion, pacing, and voice. Use when the user says "read this in a warm...

1 次安装