ElevenLabs TTS API

Overview

Best for: General-purpose voice agents and content with the largest voice library; Flash v2.5 for latency, v4 for quality.

At a glance

Figures are for Flash v2.5, the model for the streaming WebSocket (~75 ms model latency, 32 languages, $0.04/1K). v4 covers 90+ languages ($0.08/1K list, promo $0.022 until Oct 12 2026). Concurrency 6 is Flash on the Starter plan (Pro 20). Timestamps are character-level alignment. SSML parsing optional on the socket.

Features

• input streaming (WebSocket)
• multi-context WebSocket for barge-in
• character alignment / timestamps (alignment, sync_alignment)
• voice cloning
• voice design
• pronunciation dictionaries
• data residency endpoints (US, EU, India, Singapore)

Pricing

Free tier: Free / pay-as-you-go: 10,000-20,000 characters depending on model. Commercial-use terms on the free tier not re-verified; check the plan terms.

Source: elevenlabs.io

Setup

1. Create an API key in the ElevenLabs dashboard.
2. Pick a voice_id from the voice library.
3. For LLM token streaming with Flash: open wss://api.elevenlabs.io/v1/text-to-speech/{voice_id}/stream-input?model_id=eleven_flash_v2_5 with the xi-api-key header.
4. Send {"text":" "} first, then text chunks ending in a space, then {"text":""} to finish.
5. For v4 Turbo use the Text to Dialogue WebSocket instead (different message format: register voices in the first message).

Endpoint

wss://api.elevenlabs.io/v1/text-to-speech/{voice_id}/stream-input

Authentication

xi-api-key header (or authorization bearer / single_use_token query param for clients)

// npm i ws  - streams LLM-style text chunks in, saves raw PCM out
import WebSocket from "ws";
import fs from "fs";

const voiceId = "YOUR_VOICE_ID";
const url = `wss://api.elevenlabs.io/v1/text-to-speech/${voiceId}/stream-input?model_id=eleven_flash_v2_5&output_format=pcm_24000`;
const ws = new WebSocket(url, { headers: { "xi-api-key": process.env.ELEVENLABS_API_KEY } });
const out = fs.createWriteStream("out_24k_s16le.pcm");

ws.on("open", () => {
  ws.send(JSON.stringify({ text: " " }));                 // init message
  for (const t of ["Hello there. ", "This text arrives ", "in pieces, like LLM tokens. "]) {
    ws.send(JSON.stringify({ text: t }));
  }
  ws.send(JSON.stringify({ text: "" }));                  // end of input
});
ws.on("message", (raw) => {
  const msg = JSON.parse(raw.toString());
  if (msg.audio) out.write(Buffer.from(msg.audio, "base64"));
  if (msg.isFinal) ws.close();
});
ws.on("close", () => out.end());

Written from the current docs. Check the vendor's SDK version before you ship.

Warnings

Plus 12 warnings that apply to all text-to-speech, streaming APIs. See category warnings.

Limits

• Chars per request: Flash v2.5 40,000; Multilingual v2 and v4 10,000; v3 5,000 (models page)
• WebSocket inactivity_timeout default 20 s, max 180 s
• Third-party reports (Vapi support): max 5 simultaneous contexts per multi-context WebSocket; not confirmed on official pages
• Plan concurrency limits are not shown on the API pricing page; third-party lists (Free 2 ... Business 15) are unofficial
• Text to Dialogue socket waits for ~40 characters and 8 words before emitting audio unless you flush

Models and products

Docs and sources

Docs

• Models
• TTS WebSocket reference
• TTS vs Text to Dialogue WebSockets
• v4 changelog

Sources used

• elevenlabs.io/pricing/api
• elevenlabs.io/docs/overview/models
• elevenlabs.io/docs/changelog/2026/9/28
• elevenlabs.io/docs/api-reference/text-to-speech/v-1-text-to-speech-voice-id-str...
• elevenlabs.io/docs/eleven-api/guides/how-to/websockets/tts-vs-ttd-websockets