ElevenLabs Eleven v4

Name: ElevenLabs Eleven v4
Price: 0.08 USD
Availability: InStock
Author: ElevenLabs

elevenlabs/v4

Eleven v4 is ElevenLabs' most expressive text-to-speech model, with natural pacing, emotion and multilingual delivery.

Use in agent Get API key

Base price: $0.08USD / run
Execution: async
Model type: audio
Input fields: 9

Production route

Try the model

Playground

Open playground

Input

Text(string)

The text to convert to speech. Supports audio tags such as [whispering] and IPA pronunciation enclosed in forward slashes.

Output Format(string)

Output format of the generated audio. Formatted as codec_sample_rate_bitrate. Allowed values: mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192.

Seed(integer)

04294967295

Seed for best-effort reproducibility. Identical output is not guaranteed. Range: 0 to 4294967295.

Similarity Boost(number)

How closely the output follows the reference voice. Higher values increase similarity but may reduce naturalness. Range: 0 to 1.

Language Code(string)

Language code (ISO 639-1) for speech generation and text normalization.

Apply Text Normalization(string)

Whether to normalize text such as numbers and dates before generation. Allowed values: auto, on, off.

Stability(number)

Voice stability. Lower values allow more expressive delivery; higher values make delivery more consistent. Range: 0 to 1.

Voice(string)

The voice to use for speech generation

Timestamps(boolean)

Whether to return character-level timing information with the generated audio.

OutputExample

What would you like to do next?
Open original

Examples

Select an example to load its inputs and result into the playground.

Input
```
{
  "text": "Hello from SandBase."
}
```
Open result ↗

Model card

Specifications

Pricing

Base price: $0.08 / run

Context & modalities

Input: Schema-defined
Output: audio

Capabilities

Chat: Not supported
Vision: Not supported
Reasoning: Not supported
Structured output: Not supported
Function calling: Not supported
Audio input: Not supported

Access

Provider: ElevenLabs
Model ID: elevenlabs/v4
Execution: async
Base URL: https://api.sandbase.ai
API: Unified Run API
Endpoint: /v1/run

API README

ElevenLabs Eleven v4

Eleven v4, ElevenLabs' most expressive TTS model, with natural pacing, emotion, and multilingual delivery.

Fields

Field	Type	Default	Notes
`text`	string, required	—	Text to speak.
`output_format`	`mp3_22050_32` / `mp3_44100_32` / `mp3_44100_64` / `mp3_44100_96` / `mp3_44100_128` / `mp3_44100_192` / `opus_48000_32` / `opus_48000_64` / `opus_48000_96` / `opus_48000_128` / `opus_48000_192`	`mp3_44100_128`	Output file format.
`seed`	integer 0–4294967295	random	Fix it to compare prompt changes.
`similarity_boost`	number 0–1	0.75	How closely to match the voice.
`language_code`	string	—	Force a language.
`apply_text_normalization`	`auto` / `on` / `off`	`auto`	Whether to normalize text such as numbers and dates before generation.
`stability`	number 0–1	0.5	Lower is more expressive; higher is more consistent.
`voice`	string	`Rachel`	Voice name or ID.
`timestamps`	boolean	false	Return word timings.

Billing

$0.08 per started 1,000 characters, with a one-unit minimum.

Text	Price
200 characters	$0.08
1,000 characters	$0.08
2,500 characters	$0.24

Failed runs are not charged.

Prompting

Use punctuation and line breaks to shape pauses.

Also on SandBase

Other ElevenLabs voices: elevenlabs/v4-turbo, elevenlabs/v3, elevenlabs/multilingual-v2.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API

Unified Run API endpoint

https://api.sandbase.ai/v1/run

Model ID

elevenlabs/v4

# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "elevenlabs/v4",
  "text": "[excited] Hello! Welcome to Eleven v4.",
  "voice": "Aria",
  "stability": 0.5,
  "timestamps": false,
  "output_format": "mp3_44100_128",
  "similarity_boost": 0.75,
  "apply_text_normalization": "auto"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All image & video models

Model	Type	Default price	Released
ElevenLabs Eleven v4This model `ElevenLabs`	Audio	$0.08 / run	Sep 28, 2026
ElevenLabs Eleven v4 Turbo `ElevenLabs`	Audio	$0.04 / run	Sep 28, 2026
ElevenLabs Music v2.5 `ElevenLabs`	Audio	$0.75 / run	Sep 14, 2026
ElevenLabs Music v2 `ElevenLabs`	Audio	$0.75 / run	Sep 14, 2026
Scribe V2 `ElevenLabs`	Audio	$0.01 / run	Jan 14, 2026
ElevenLabs Music `ElevenLabs`	Audio	$0.60 / run	Dec 22, 2025

Questions

FAQ

How do I call ElevenLabs Eleven v4 through SandBase?

Create a SandBase API key, then send requests with the model ID "elevenlabs/v4" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate ElevenLabs account?

No. One SandBase API key and balance gives you access to ElevenLabs Eleven v4 and the other models in the catalog; you do not need to sign up with ElevenLabs separately.