About Eleven v4 Turbo
Eleven v4 Turbo is the low-latency variant of Eleven v4, producing expressive speech in more than 90 languages at about 100 ms median inference latency.
It shares Eleven v4's audio tags, voice settings, and language coverage, so [whispering], [laughing], and similar tags direct delivery the same way. It fits voice agents, assistants, interactive characters, and bulk narration where speed and cost matter. A single request takes up to 10,000 characters.
| Metric | Value |
|---|---|
| Context Length | 10,000 characters |
| Multilingual | Yes, 90+ languages |
Ready to build with Eleven v4 Turbo?
Try Eleven v4 Turbo in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "elevenlabs-eleven-v4-turbo",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'Request parameters
Every field Eleven v4 Turbo accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/chat/completions| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Text to speak, up to 10,000 characters. Put audio tags in square brackets before a line to direct its delivery, e.g. [whispering], [excited], [sigh]. |
voice_id | string | Yes | "JBFqnCBsd6RMkjVDRZzb" | The voice that speaks the text.pNInz6obpgDQGcFmaJgBXb7hH8MSUJpSbSDYk0k2hpp4J3VqNfWAUOO0d1UspqHfZKP75CvOlQylNhV4nPczCjzI2devNBz1zQrbN2lVS1w4EtoT3dr4eOWOIKne3meq5aSn9XLyUdCDiP95p4xoKVk53GoZ742BonwK4e9ZLuTAKqWW03F9cjVigY5qzO86Huf0OWalJBFqnCBsd6RMkjVDRZzbSOYHLrjzK2X1ezoPC6crcgSgspJ2msm6clMCkdW9FGY2WhTYpPnrIDTdsKH5TX3LPaxmHKxFdv7VOQHJpFZP5JQG7iQjIQuC4BkuXrExE9yKIg1WjnnlVkGXSAz9YHcvj6GT2YYXdXwwCwhRBWXzGAHq8TQ4Fs17EXAVITQu4vr4xnSDxMaLbIHbv24MWmeRgasZH58o |
language_code | stringnullable | No | — | Optional ISO 639-1 language code (e.g. en, es, ja) to force the language and its text normalization. Leave empty to detect it from the text. |
stability | number | No | 0.5 | Lower values give more varied, expressive delivery; higher values keep the performance consistent across generations. Range: 0 – 1 |
similarity_boost | number | No | 0.75 | How closely the output follows the voice. Higher values match it more closely at some cost to naturalness. Range: 0 – 1 |
apply_text_normalization | string | No | "auto" | Whether numbers, dates, and abbreviations are spelled out before speaking.autoonoff |
seed | integernullable | No | — | Optional seed for best-effort deterministic output. Range: 0 – 4294967295 |