Skip to main content
ElevenLabsSep 29, 2026

ElevenLabs TTS v4

elevenlabs-tts-v4Anonymized

Generate expressive text-to-speech audio using ElevenLabs Eleven-v4. High-quality voices with audio tag support and automatic text normalization.

$92.00
per 1M characters
$4.55
per hour of speech
20
voices, or any voice ID
20 voices

Names are case-sensitive. Any ElevenLabs voice ID works too. Pick one to use it in the request below.

Capabilities

Formatsmp3, mp3 by default
QueuedQuote, queue and retrieve, like music
Any ElevenLabs voicePass its voice ID as voice

Pricing

Billed per 1M characters of input, in USD.

Input$92.00per 1M characters
Speech, about$0.0759per minute
Speech, about$4.55per hour

Estimated at 825 characters a minute, about 150 spoken words.

Estimate a script

121 minof speech, estimated
$9.20to speak them

Against other speech models

How it comparesamong 15 speech models
Pricecheaper than 36%$92.00
Voicesmore than 50%20

Further right is better. Hover a dot for its model.

Specs

Model ID
elevenlabs-tts-v4
Endpoint
POST /api/v1/audio/queue
Voices
20, or any ElevenLabs voice ID
Formats
mp3 · default mp3
Streaming
No, it runs as a queued job
Voice cloning
No
Privacy
Anonymized
Weights
Closed
Added
Sep 29, 2026

Other versions

  1. ElevenLabs TTS v3Feb 2026
  2. ElevenLabs TTS v4Sep 2026

Compare

Every text-to-speech model on Venice, cheapest first.

ModelVoicesFormatsPrivacyPer 1M characters
Kokoro Text to Speech54mp3, opus, aac, flac, wav, pcmPrivate$3.50
Inworld TTS-1.5 Max14wavAnonymized$12.50
xAI TTS v126mp3, wav, pcmPrivate$18.75
ElevenLabs TTS v4 Turbo20mp3Anonymized$46.00
Gradium TTS12wav, pcm, opusAnonymized$47.50
Chatterbox HD (Resemble AI)9wavPrivate$50.00
ElevenLabs Turbo v2.521mp3Anonymized$62.50
Orpheus TTS8wavPrivate$62.50
Qwen 3 TTS 0.6B9mp3Private$87.50
ElevenLabs TTS v420mp3Anonymized$92.00
Qwen 3 TTS 1.7B9mp3Private$113
ElevenLabs Multilingual v220mp3Anonymized$115
ElevenLabs TTS v320mp3Anonymized$115
MiniMax Speech-02 HD15mp3, pcm, flacAnonymized$125
Gemini 3.1 Flash TTS30mp3, opus, wavAnonymized$188

Quickstart

This model runs as a queued job: queue the text, then poll for the audio.

  1. 1QuotePOST /audio/quoteOptional. Prices the job in USD without charging for it.
  2. 2QueuePOST /audio/queueChecks and charges the job, then returns a queue_id at once.
  3. 3RetrievePOST /audio/retrievePoll it with the queue_id until the audio is ready.
# 1. Queue the job (returns a queue_id)
curl https://api.venice.ai/api/v1/audio/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "elevenlabs-tts-v4",
"prompt": "Private AI for everyone.",
"voice": "Aria"
}'

# 2. Poll until the audio is ready (JSON with the status until then)
curl https://api.venice.ai/api/v1/audio/retrieve \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "elevenlabs-tts-v4", "queue_id": "<queue_id>" }' --output audio.mp3
Base URL https://api.venice.ai/api/v1

Parameters

ParameterValuesNotes
modelelevenlabs-tts-v4Required
promptThe text to speakRequired
voice20 voices, or a voice IDThe model’s own by default