Skip to content
ElevenLabs logo

Eleven Flash v2.5

Text-to-Speech • ElevenLabs

View as MarkdownAgent setup

Model ID

Use with the Workers AI binding, the AI Gateway REST API, or the Unified API.

Calling the provider directly? Use the provider's model name instead, including with provider-native endpoints or the provider's own SDK. For example, Anthropic's name for anthropic/claude-opus-4.8 is claude-opus-4-8.

  • Third-party

ElevenLabs' low-latency Flash v2.5 text-to-speech model for fast multilingual speech generation.

Model Info
Terms and Licenselink ↗
More informationlink ↗
Pricing
  • Per character$0.00005

Usage

const response = await env.AI.run(
  'elevenlabs/eleven-flash-v2-5',
  {
    text: 'Thanks for contacting Cloudflare AI Gateway support. I can help you compare providers, review request logs, or troubleshoot model routing.',
    voice_id: 'JBFqnCBsd6RMkjVDRZzb',
    output_format: 'mp3_44100_128',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "elevenlabs/eleven-flash-v2-5",
  "input": {
    "text": "Thanks for contacting Cloudflare AI Gateway support. I can help you compare providers, review request logs, or troubleshoot model routing.",
    "voice_id": "JBFqnCBsd6RMkjVDRZzb",
    "output_format": "mp3_44100_128"
  }
}'
{
  "state": "Completed",
  "result": {
    "audio": "https://examples.aig.cloudflare.com/elevenlabs/eleven-flash-v2-5/ai-gateway-assistant.mp3"
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

Parameters

text
stringrequiredminLength: 1maxLength: 10000The text to convert into speech.
voice_id
stringrequiredminLength: 1The ElevenLabs voice ID to use for generation.
output_format
stringenum: mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96, opus_48000_128, opus_48000_192, opus_48000_32, opus_48000_64, opus_48000_96
language_code
stringISO 639-1 language code to enforce.
seed
integerminimum: 0maximum: 4294967295
previous_text
string
next_text
string
apply_text_normalization
stringenum: auto, on, off
audio
stringURL to the generated audio file.

API Schemas (Raw)

Input
Output

Was this helpful?