ElevenLabs: Eleven Flash v2.5

Name: Eleven Flash v2.5
Author: ElevenLabs

elevenlabs/eleven-flash-v2-5

active tts 1 provider

Playground

ElevenLabs' ultra-low-latency model in 32 languages, ideal for conversational use cases.

AuthorElevenLabs

Languages32 languages

VoicesLoading...

Response formatsSynchronous: MP3 · WAV · PCM · Opus · µ-law · A-law
Streaming: MP3 · PCM · Opus · µ-law · A-law

Statusactive

Quick start

Eleven Flash v2.5

Create an API key

Create API key

Make a request

Pick an SDK, request mode, and language. The model and provider route are already filled in.

ElevenLabs SDK streaming TTS

Routes the ElevenLabs SDK through allmodels and streams the audio response.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "elevenlabs/eleven-flash-v2-5",
  outputFormat: "mp3_44100_128"
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}

Use native SDK parameters

When the selected SDK matches the provider, pass provider parameters as native SDK fields. Provider preferences are only needed for cross-provider SDK usage.

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer 1k charactersLatencyiModesUptime

ElevenLabs 14 params

elevenlabs

$0.05

—

Synchronous · Streaming

ElevenLabs

14 documented provider parameters for this route.

Pricing

ModeLanguagePer 1k characters

Low-Latency TTS Any $0.05

Parameters

text body · unknown · required

Mapped from allmodels parameter "input".

voice_id body · unknown · required

Mapped from allmodels parameter "voice".

apply_language_text_normalization body · unknown · optional

Mapped from allmodels parameter "language_text_normalization".

apply_text_normalization body · unknown · optional

Mapped from allmodels parameter "text_normalization".

language_code body · unknown · optional

Mapped from allmodels parameter "language".

model_id body · unknown · optional

Mapped from allmodels parameter "model".

next_request_ids body · unknown · optional

Mapped from allmodels parameter "next_request_ids".

next_text body · unknown · optional

Mapped from allmodels parameter "next_text".

output_format body · unknown · optional

Mapped from allmodels parameter "response_format".

previous_request_ids body · unknown · optional

Mapped from allmodels parameter "previous_request_ids".

previous_text body · unknown · optional

Mapped from allmodels parameter "previous_text".

pronunciation_dictionary_locators body · unknown · optional

Mapped from allmodels parameter "pronunciation_dictionary".

seed body · unknown · optional

Mapped from allmodels parameter "seed".

voice_settings body · unknown · optional

Mapped from allmodels parameter "voice_settings".

Supported languages

32 languages

English en

Japanese ja

Chinese zh

German de

Hindi hi

French fr

Korean ko

Portuguese pt

Italian it

Spanish es

Russian ru

Indonesian id

Dutch nl

Turkish tr

Filipino fil

Polish pl

Swedish sv

Bulgarian bg

Romanian ro

Arabic ar

Czech cs

Greek el

Finnish fi

Croatian hr

Malay ms

Slovak sk

Danish da

Tamil ta

Ukrainian uk

Hungarian hu

Norwegian no

Vietnamese vi

Voices

Features

Text to speech

Generates spoken audio from text input.

text_to_speech

Streaming

Streams synthesized audio incrementally over a persistent connection (WebSocket/SSE).

streaming

Synchronous

Synthesizes speech from fully-submitted text in a single synchronous request.

synchronous

Multilingual

Supports 32 languages.

multilingual

Low latency

Designed for lower-latency speech generation use cases.

low_latency

Fine-tuning

Supports provider-managed fine-tuning for this model.

fine_tuning

Code

ElevenLabs SDK streaming TTS

Routes the ElevenLabs SDK through allmodels and streams the audio response.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const stream = await client.textToSpeech.stream("voice_id", {
  text: "I'm sorry, Dave. I'm afraid I can't do that.",
  modelId: "elevenlabs/eleven-flash-v2-5",
  outputFormat: "mp3_44100_128"
});

const reader = stream.getReader();
for (;;) {
  const { done, value } = await reader.read();
  if (done) break;
  // Write value to your response, file, or audio playback pipeline.
}