About ElevenLabs v4
ElevenLabs v4 is ElevenLabs' text-to-speech model for narration, lessons and character lines. It reads up to 10,000 characters per request in one of 21 preset voices, across more than 90 languages, and follows inline cues such as [whispers].
Call it with the model name elevenlabs/v4/text-to-speech on POST /jobs/createTask, from $0.096.
Introduction
ElevenLabs v4 API for directed narration
ElevenLabs v4 API exposes Eleven v4, ElevenLabs' text-to-speech model, as elevenlabs/v4/text-to-speech. Supply a script and a premade voice to produce a single-speaker recording for a lesson, product video or character line.
ElevenLabs says v4 targets content creation and long-form audio in its September release note. This endpoint accepts up to 10,000 text characters; custom voice IDs and multi-speaker dialogue input are unavailable here.
Request example: an English character line
Call elevenlabs/v4/text-to-speech with the following JSON as the endpoint input.
{
"text": "[whispers] Keep the lantern covered until we reach the bridge.",
"voice_id": "Daniel",
"language": "en",
"text_normalization_mode": "auto",
"output_format": "mp3_22050_32",
"seed": 7
}Use the page's API request example to submit these input fields with your credentials. The public invocation name above identifies the model; this input object does not describe the surrounding HTTP request envelope.
Response example: the observed audio result
Our separate 84-character Daniel request produced an MP3 recording lasting 5.17 seconds.
Audio: MP3
Selected output_format: mp3_22050_32
Recording duration: 5.17 seconds
Request completion: approximately 4.7 secondsParameters for a single-voice recording
The required input is text; the other fields select the voice, language, delivery or export behavior. Use these fields to prepare your narration.
| Parameter | Accepted setting or role | Practical choice |
|---|---|---|
text | Required; up to 10,000 characters | Write the spoken script; place [whispers] or [laughs] beside the relevant passage. |
voice_id | 21 premade voices; default Roger | Audition Daniel, Sarah or Lily with the same excerpt. |
language | auto or one of 91 language codes | Choose en for an English take or select the intended language code. |
stability | Delivery variation | Adjust against a fixed passage; see the publisher explanation below. |
similarity_boost | Adherence to the selected voice | Listen for the voice characteristics you want to retain. |
clone_strength | No effect on premade voices | Omit it for this endpoint's cast. |
text_normalization_mode | auto, on, off | Check how dates, quantities and abbreviations are spoken. |
output_format | Nine options; default mp3_44100_128 | mp3_22050_32 matches the format in our v4 measurement. |
seed | A seed for comparing changes | Reuse it when adjusting one element; identical audio is not promised. |
Getting a performance you can publish
Start with a short excerpt containing the same names, numbers and tone as the intended production. A lesson instruction such as “Open the worksheet and underline the verbs” gives you a focused passage to audition before recording the surrounding explanation.
- Choose a voice before rewriting the delivery cues.
- Add an inline tag where the performance should shift, then listen to that transition.
- Set the intended language and check number readings with your chosen normalization mode.
- Keep a seed fixed while changing a single setting, and save the settings beside the selected take.
ElevenLabs says lower stability allows greater emotional variation and similarity_boost controls adherence to the original voice in its voice settings documentation. Judge the resulting delivery by listening to your passage rather than assuming a setting fits every voice.
Troubleshooting an awkward read
Revise the relevant input when a recording sounds wrong: spell out an ambiguous date, remove competing cues or audition another premade voice. ElevenLabs says complex numbers and abbreviations can be mispronounced in its speech guidance.
Test evidence and model selection
Our November 13, 2026 calls provide two concrete samples with different inputs. Each contained one audio tag; these results are observations rather than a controlled comparison.
| Variant | Input and voice | Language / seed | Format | Audio length | Completion |
|---|---|---|---|---|---|
| Eleven v4 | 84 characters; Daniel | en / 7 | mp3_22050_32 | 5.17 seconds | About 4.7 seconds |
| Eleven v4 Turbo | 75 characters; Sarah | Not specified in the fact sheet | mp3_44100_128 | 3.40 seconds | About 7.6 seconds |
Choose v4 for reviewed final takes, or consider Eleven v4 Turbo for drafts, high-volume work and latency-sensitive flows. The Turbo measurement above does not reverse that use-case guidance: script, voice and export settings differed.
Recording rights
Publish recordings from scripts and voices you are entitled to use, without impersonating a real person. Review the completed audio before publishing it as part of a course, application or promotional video.
Request parameters
| Parameter | Required | Description |
|---|---|---|
seed | No | Use the same seed and settings for more controlled comparisons. ≥ 0 · ≤ 4294967295 |
text | Yes | The words to be spoken, exactly as written. |
language | No | The language of the speech. auto · af · am · ar · hy · as · ast · az · be · bn · bs · bg · my · yue · ca · ceb · hr · cs · da · nl · en · et · fil · fi · fr · ff · gl · ka · de · el · gu · ha · he · hi · hu · is · id · it · ja · jv · kam · kn · kk · ko · ky · lo · lv · ln · lt · lg · lb · mk · ms · ml · mt · zh · mi · mr · mn · ne · no · oc · or · ps · fa · pl · pt · pa · ro · ru · sr · sn · sd · sk · sl · so · ckb · es · sw · sv · tg · ta · te · th · tr · uk · ur · uz · vi · cy · wo · zu · Default: auto |
voice_id | No | Pick from the available voices. Adam · Alice · Bella · Bill · Brian · Callum · Charlie · Chris · Daniel · Eric · George · Harry · Jessica · Laura · Liam · Lily · Matilda · River · Roger · Sarah · Will · Default: Roger |
stability | No | How steady the delivery is. Lower is more expressive and more varied. ≥ 0 · ≤ 1 · Default: 0.5 |
output_format | No | File type of the result. mp3_44100_128 · mp3_44100_64 · mp3_22050_32 · opus_48000_128 · pcm_24000 · pcm_16000 · wav_44100 · ulaw_8000 · alaw_8000 · Default: mp3_44100_128 |
clone_strength | No | How strongly a professional voice clone is applied. No effect on preset voices. ≥ 0 · ≤ 1 |
similarity_boost | No | How closely the speech sticks to the chosen voice. ≥ 0 · ≤ 1 · Default: 0.75 |
text_normalization_mode | No | Whether numbers, dates and abbreviations are spelled out before reading. auto · on · off · Default: auto |
Pricing
Prices are in USD and charged to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.
| Option | USD per 1,000 characters |
|---|---|
| Standard | $0.096 |
Send the same request body to POST /jobs/quote to see the estimated and maximum USD charge before running. A quote does not run the task or charge your balance.
API quick start
Call the ElevenLabs v4 API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow-. API calls are billed in USD from your PopNow balance.
- Send the request. POST /jobs/createTask with model elevenlabs/v4/text-to-speech and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "elevenlabs/v4/text-to-speech",
"input": {
"text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
"voice_id": "Roger",
"language": "auto"
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.
ElevenLabs v4 API questions
How much does the ElevenLabs v4 API cost?
ElevenLabs v4 costs $0.096 per 1,000 characters. API usage is charged in USD to your PopNow balance. When a task is accepted, we reserve the maximum quoted amount from your API balance. On completion, we charge for actual usage, never more than the hold, and release the remainder. If the task fails, the hold is released.
What is the model name for ElevenLabs v4 in the API?
Put elevenlabs/v4/text-to-speech for Text to Speech in the model field of POST /jobs/createTask.
What does the ElevenLabs v4 API generate?
The ElevenLabs v4 API generates a recording of your text spoken by one premade voice. Eleven v4 is ElevenLabs' text-to-speech model, released on September 28, 2026. This endpoint accepts scripts up to 10,000 characters and offers inline audio tags to guide delivery.
How do I call the ElevenLabs v4 API with my script?
Call elevenlabs/v4/text-to-speech with the required text field and your selected voice_id. For an English narration, choose Daniel, set language to en and select an output_format such as mp3_22050_32. The endpoint guide below provides a JSON input example and the measured audio result from a separate test.
When should I choose Eleven v4 instead of v4 Turbo?
Choose Eleven v4 for final narration and character takes where you want to review the performance before publishing. ElevenLabs says v4 is intended for content creation and long-form audio, while Turbo targets interactive applications. Our v4 and Turbo samples used different scripts, voices and formats, so their completion times do not establish a speed ranking.
Can I use a cloned voice or several speakers?
This endpoint offers 21 premade voices and one speaker per request. Roger is the default, with choices including Sarah, Daniel and Lily. Custom voice IDs and multi-speaker dialogue input are unavailable here, and clone_strength has no effect on these premade voices.
How do square-bracket audio tags affect a read?
Inline tags such as [whispers] and [laughs] guide the delivery within the text. Put a cue immediately before the passage you want to direct, then listen to the result in context. Our recorded test used one tag; it does not establish how every tag combination will behave.
What are the limits of the ElevenLabs v4 API?
Text length (characters): 10,000; Voices: 21; Languages: 91. Requests outside these limits are rejected before anything is charged.
Can I try ElevenLabs v4 without writing code?
Run ElevenLabs v4 in the Playground with your API USD balance, without an API key. Each run appears in your developer history with its matching code.
All ElevenLabs models
ElevenLabs v4 Turbo has the same voices and settings at half the price per character. You can draft with Turbo and render the final take with v4.
- ElevenLabs Scribe V3 APIWord-level transcripts with speaker labels and sound events in 102 languagesFrom $0.0002 per second
- ElevenLabs Audio Isolation APIIsolate clear speech from noisy audio or video, delivered as an MP3From $0.0022 per second
- ElevenLabs v4 Turbo APIFaster ElevenLabs v4 speech with the same 21 voices and 90+ languagesFrom $0.048 per 1,000 characters
- ElevenLabs v4 APIElevenLabs v4 speech in 21 voices and 90+ languages, up to 10,000 charactersFrom $0.096 per 1,000 characters
- ElevenLabs Voice Changer APIRe-voice a recording in one of 41 preset voices, same words and timingFrom $0.0048 per second
- ElevenLabs Dubbing APIDub a recording or a video's soundtrack into 33 languages, up to 15 minutesFrom $0.012 per second