About Eleven v4
Eleven v4 is a text-to-speech model built for expressive, emotionally rich speech across more than 90 languages.
Inline audio tags such as [whispering], [laughing], or [quietly curious] direct the delivery line by line, and punctuation and ellipses shape pacing. It suits character voiceover for games and animation, audiobooks and long-form narration, and multilingual content that has to keep one voice consistent across languages. A single request takes up to 10,000 characters, roughly ten minutes of audio. Two voice settings, Stability and Similarity, control how varied the delivery is and how closely it follows the voice.
| Metric | Value |
|---|---|
| Context Length | 10,000 characters |
| Multilingual | Yes, 90+ languages |
Ready to build with Eleven v4?
Try Eleven v4 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",
"messages": [
{
"role": "user",
"content": "Try sending a message."
}
]
}'Request parameters
Every field Eleven v4 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 |