Maya

Reads text aloud Stream

Liveby fal

Maya1 is a state-of-the-art speech model by Maya Research for expressive voice generation, built to capture real human emotion and precise voice design.

Guide: Text to speech APIs compared

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

CodexClaude CodeAny agent with a terminal

Read this paragraph aloud in a warm voice and send me the audio.

More examples

Turn my blog post into an audio file I can share.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call, input and output

Text to speech API by fal, callable through Superpowers. It costs $0.011 per 5s clip, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "fal.maya-stream", or over MCP with run_tool. 12 other providers in this category take the same input and can be compared side by side.

Tool id
Price per call: $0.011 / 5s clip

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.maya-stream","input":{"prompt":"","text":""},"idempotency_key":"example-request-1"}'

Input

8 fields · 2 required

{
  "type": "object",
  "required": [
    "text",
    "prompt"
  ],
  "properties": {
    "output_format": {
      "type": "string",
      "description": "Output audio format. 'mp3' for browser-playable audio, 'wav' for uncompressed audio, 'pcm' for raw PCM (lowest latency, requires client-side decoding).",
      "default": "mp3",
      "enum": [
        "mp3",
        "wav",
        "pcm"
      ]
    },
    "max_tokens": {
      "type": "integer",
      "description": "Maximum number of SNAC tokens to generate (7 tokens per frame). Controls maximum audio length.",
      "default": 2000
    },
    "top_p": {
      "type": "number",
      "description": "Nucleus sampling parameter. Controls diversity of token selection.",
      "default": 0.9
    },
    "prompt": {
      "type": "string",
      "description": "Description of the voice/character. Includes attributes like age, accent, pitch, timbre, pacing, tone, and intensity. See examples for format."
    },
    "text": {
      "type": "string",
      "description": "The text to synthesize into speech. You can embed emotion tags anywhere in the text using the format <emotion_name>. Available emotions: laugh, laugh_harder, sigh, chuckle, gasp, angry, excited, whisper, cry, scream, sing, snort, exhale, gulp, giggle, sarcastic, curious. Example: 'Hello world! <exci"
    },
    "sample_rate": {
      "type": "string",
      "description": "Output audio sample rate. 48 kHz uses upsampling for higher quality audio, 24 kHz is native SNAC output (faster, lower latency).",
      "default": "24 kHz",
      "enum": [
        "48 kHz",
        "24 kHz"
      ]
    },
    "temperature": {
      "type": "number",
      "description": "Sampling temperature. Lower values (0.2-0.5) produce more stable/consistent audio. Higher values add variation.",
      "default": 0.4
    },
    "repetition_penalty": {
      "type": "number",
      "description": "Penalty for repeating tokens. Higher values reduce repetition artifacts.",
      "default": 1.1
    }
  }
}

Normalized output

Example for this type of tool

The shape tools of this type share in normalized. Agents read it from GET /v1/tools/fal.maya-stream or MCP inspect_tool.

{
  "type": "object",
  "properties": {
    "audio_url": {
      "type": "string"
    },
    "chars": {
      "type": "integer"
    }
  },
  "required": [
    "audio_url",
    "chars"
  ]
}