−46% vs fal.aiSeedance video for less than fal.aiNo subscription. A clip that fails is never charged.Get $1 in free credits. Top up from just $3.
toolfare
Start free
Bought by toolfare · quoted first

Have your AI turn a script into spoken audio, in a voice you choose.

Turn text into speech from Claude, ChatGPT, Cursor, Codex or your own code: three models, a searchable list of voices, and controls for speed, stability and style. The audio comes back in the same call. No voice-platform account or key of your own — each call is quoted before it runs and paid from one toolfare balance.

Start freeUse the API

1Connect your AI app

Pick the app you use. You do this once, and every API on toolfare is then available in it.

Add toolfare as a connector in Claude

Add to Claude
https://api.toolfare.ai/mcp
  1. 1Open Customize → Connectors and choose "Add custom connector".
  2. 2Paste this URL as the remote MCP server URL.
  3. 3Leave the OAuth client id and secret under Advanced settings empty.
  4. 4Complete the browser authorization, then return to your conversation.

Custom connectors are available on Free, Pro, Max, Team and Enterprise. A Free account may hold one custom connector in total.

Claude’s own instructions

2What to ask

Copy a prompt into your AI app once you’re connected. It picks the right one of the 2 tools and tells you the price first.

  • Speech from your text, in the same call

    From $0.12

    Low-latency speech

    • “Read this paragraph aloud in a warm female voice.”
    • “Make a 20-second voiceover from this script, a little faster than normal.”
    • “Say this greeting in Chinese for our support line.”

  • Find the right voice

    Free

    List available voices

    • “Which voices are available for narration?”
    • “Find me a deep British male voice.”

Use it when

  • You need a voiceover or narration for a short clip, demo or explainer.
  • Your app or agent should read a reply or notification aloud.
  • You want to try a few voices on the same line before choosing one.

Look elsewhere when

Text to Speech directly, or through toolfare

Directly

  • An account, plan and API key with a voice platform
  • Monthly character allowances that reset whether you use them or not
  • Your own code to call the API and save the audio

Through toolfare

  • Pay per call, quoted before it runs, with no monthly allowance
  • No voice-platform key to hand to an agent
  • Transcription, dubbing and music on the same balance

You get the models and voices this gateway exposes, a short text per call, and no voice cloning or studio editor — for long audiobooks or custom voices, a voice platform’s own plan fits better.

Limits

  • Each call takes at most 1,200 units of spoken length: a letter or space counts 1, a CJK character 4, a digit 12. Split long scripts across calls.
  • Digits cost far more units than letters, so spelling numbers out fits more into one call.
  • Voices are chosen by ID; list them with the voices tool first. On tts-v3, stability accepts only 0, 0.5 or 1.
  • Pay as you go from your toolfare balance, in US dollars; there is no subscription. A call runs when your balance covers its quote.
Text to Speech documentation

Questions

Any voice the voices tool lists. Your agent can search that list, for example for “calm narrator”, and pass the voice ID to the speech tool.

Up to 1,200 units of spoken length — roughly a long paragraph of English, less for Chinese or text with many digits. Split longer scripts into several calls.

Yes. The speech tool returns its audio in the same call; there is no task to collect.

toolfare makes no claims beyond what the model allows; check the model’s terms for your use.

Each tool’s current price is shown on this page and quoted before the call runs.

Related sources