BlockRun
ElevenLabs · Text to Speech

ElevenLabs Turbo v2.5 API

Balanced quality and latency (~250ms) for interactive use cases. 32 languages.

$0.0535 per 1,000 characters · priced before it runs · no subscription

About ElevenLabs Turbo v2.5

ElevenLabs Turbo v2.5 is a text-to-speech model from ElevenLabs that reads up to 40,000 characters per request aloud. It is billed on the characters you send, $0.0535 per 1,000 characters. You can call it without an account, an API key or a subscription.

Use ElevenLabs Turbo v2.5 for

  • Voice for agents and assistants that answer out loud
  • Narration for articles, courses and product videos
  • Accessibility: reading an app's own text aloud on demand

ElevenLabs Turbo v2.5 specs

Endpoint
POST /api/v1/audio/speech
Price
$0.0535 per 1,000 characters
Longest input
40,000 characters per request
Billing basis
Characters of input text

How to call ElevenLabs Turbo v2.5

Pass elevenlabs/turbo-v2.5 as the model field. The first request returns a 402 with the exact price; a signed retry runs it, and the client libraries fold the two into one call — how the payment works. Request and response shapes are in the docs.

curl -X POST https://blockrun.ai/api/v1/audio/speech \
  -H "Content-Type: application/json" \
  -d '{"model": "elevenlabs/turbo-v2.5", "input": "Your order has shipped and arrives on Friday."}'

ElevenLabs Turbo v2.5 or another speech model

Every speech model here takes the same request on the same endpoint, so trying another is a one-line change to the model field. The Text to Speech API page lists all of them side by side.

ElevenLabs Turbo v2.5 API questions

How much does the ElevenLabs Turbo v2.5 API cost?

$0.0535 per 1,000 characters, including the per-call transaction fee. The exact price is quoted in the 402 response before anything is generated, and you pay per request with no subscription.

Do I need an API key to use ElevenLabs Turbo v2.5?

No. Each request carries its own payment, so an agent or script can call ElevenLabs Turbo v2.5 with no account and no key. Teams that prefer one can use an API key with card or invoice billing instead.

How do I call ElevenLabs Turbo v2.5?

Send a POST to /api/v1/audio/speech with "model": "elevenlabs/turbo-v2.5". The request shape is shown above, and the same endpoint serves every speech model on the catalog, so switching models is a one-line change.

How long can the text be for ElevenLabs Turbo v2.5?

Up to 40,000 characters per request. Longer text can be split across requests, each priced on its own.

ElevenLabs Turbo v2.5 or another model — which should I use?

Compare it with ElevenLabs Multilingual v2 ($0.106 per 1,000 characters), ElevenLabs v3 ($0.106 per 1,000 characters), Seed Audio 1.0 (about $0.316 per 1,000 characters) in the table above. They take the same request on the same endpoint, so you can try two on one prompt and keep the one you prefer.

Two ways to run this

Get an API key

Sign in, get a key, and call the same endpoints with usage billed to your account. For teams that want one invoice instead of one wallet.

Get an API key 

Or let your agent pay per call, in USDC

No account, no API key. Three steps, and the last one is the request this page is about.

  1. 01
    Point your agent at BlockRun

    Install ClawRouter, or add the BlockRun MCP server to Claude Code, Cursor, Codex or OpenClaw. Any OpenAI-compatible client works too — change the base URL, nothing else.

    curl -fsSL https://blockrun.ai/ClawRouter-update | bash
  2. 02
    Fund a wallet with USDC

    Send USDC to a wallet on Base, Solana or Arc. There is no account to create and no API key to issue: the wallet is the account, and it pays per call.

  3. 03
    Call ElevenLabs Turbo v2.5

    The first call returns HTTP 402 with the exact price, your agent signs it, and the answer comes back. Payment settles on-chain; nothing is charged if the call fails.

    curl -X POST https://blockrun.ai/api/v1/audio/speech \
      -H "Content-Type: application/json" \
      -d '{"model": "elevenlabs/turbo-v2.5", "input": "Your order has shipped and arrives on Friday."}'