Skip to main content

elevenlabs/v4/text-to-speech

Eleven v4 is ElevenLabs' text-to-speech model for turning a script into single-speaker audio. This endpoint combines premade voice selection with language, delivery and export controls.

From $0.096/1,000 characters

Workbench

Input

Text to speech
126/10000
Supply the spoken script in this required field, with no more than 10,000 characters. Square-bracket cues such as [whispers] belong beside the words they should direct. at least 1 characters · at most 10000 characters

126 characters

Choose from 21 premade voices; Roger is selected by default. Audition the same passage with Daniel, Sarah or Lily before settling on the cast.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result
0:00 / –:––

Related models and next tasks

Missing the model you need?

TEXT-TO-SPEECH API

Direct the spoken performance of a finished script with a premade voice and inline audio cues.

Key numbers

Text character limit
10,000
Premade voice auditions
21
Language code choices
91
Our Daniel sample audio
5.17 s

Before you spend

All modes

Use scripts and voices you have the right to use, and do not impersonate real people. Our November 13, 2026 sample measured a short English recording; it does not verify every language, voice or full-length narration.

Text to speech

Each Eleven v4 request accepts up to 10,000 text characters and uses one of 21 premade voices. Multi-speaker dialogue input and custom voice IDs are unavailable on this endpoint; clone_strength has no effect on its premade cast.

What it does

Performance direction

Put a cue beside the spoken line

Eleven v4 accepts square-bracket audio tags within text, including [whispers] and [laughs]. Begin with a passage whose wording already conveys the intended mood, then add a cue where the delivery should change. Our test used one tag, so audition additional combinations before building a full scene around them.

Casting controls

Audition within a 21-voice cast

The voice_id selection supplies 21 premade voices, with Roger selected by default. Compare Daniel, Sarah or Lily against the same passage before revising the script. ElevenLabs says stability shapes variation and similarity_boost shapes adherence to the chosen voice; clone_strength does not alter premade voices here.

Measured recording

A Daniel take with recorded timings

On November 13, 2026, our 84-character v4 call used Daniel, language en, seed 7 and mp3_22050_32. It returned 5.17 seconds of MP3 audio and finished in about 4.7 seconds. That observation is a reference for one request, with no claim about longer scripts or every voice.

Language and export

Choose the reading and the audio format

Language selection offers auto or 91 codes, while output_format has nine options and defaults to mp3_44100_128. Use text_normalization_mode to decide how numbers and abbreviations are expanded. Check a passage containing your actual names and dates before producing the rest of the script.

Where it fits

  • A lesson with an exact instruction

    Submit "Open the worksheet and underline the verbs in the second paragraph" with Daniel and language en. Use the returned narration as the spoken instruction beside that course exercise.

  • A product walkthrough

    Send "Select Export, choose the destination folder, then confirm the file name" with Sarah. The resulting voice-over can accompany a screen recording of those three actions.

  • A quiet game character line

    Give Lily the text "[whispers] The guard is still outside the gate." The output is a single character take that you can audition against the game scene.

  • A localized app instruction

    Provide your approved translation of a sign-in instruction in text and select its language code. The endpoint returns spoken audio for that language version; translation remains a separate preparation step.

  • An advertisement closing line

    Use "Bring your next idea to the workshop this Saturday" as the script and audition a premade voice. Place the selected recording at the close of a promotional video after checking the delivery.

Model reference

ElevenLabs v4 API reference

ElevenLabs v4 API specifications

Speech model publisher
ElevenLabs
Model name and release
Eleven v4; September 28, 2026
Public text-to-speech API name
elevenlabs/v4/text-to-speech
Required script field
text; up to 10,000 characters
Premade voice selection
21 voices; Roger by default
Language selection
auto or one of 91 language codes
Audio format selection
9 options; default mp3_44100_128
Text normalization modes
auto, on, off
Inline delivery cues
Square-bracket audio tags, including [whispers] and [laughs]
Unsupported voice inputs
Custom voice IDs and multi-speaker dialogue
Usage measurement
Characters of text
Recorded Daniel result
84 characters; 5.17-second MP3; about 4.7 seconds to finish

How to call the ElevenLabs v4 API

  1. Prepare a passage for narration

    Write the spoken words in text, staying within 10,000 characters. Add [whispers] or [laughs] where a delivery cue serves the scene.

  2. Choose the voice and language

    Select a premade voice such as Daniel or Lily, or leave Roger selected. Use auto for language detection or select the intended code from the 91 choices.

  3. Call the speech endpoint

    Invoke elevenlabs/v4/text-to-speech with text, voice_id and output_format, following the JSON input in the endpoint guide. For an English MP3, set language to en and output_format to mp3_22050_32.

  4. Review the take before publishing

    Listen for names, number readings and the transition around each audio tag. Save the chosen settings with the audio and compare a single revision at a time.

The short version

Begin an Eleven v4 narration with a passage that contains the names, dates and emotional cues your finished script needs. Choose a premade voice, set the language and output format, and listen before extending the recording to the remaining sections. Our Daniel sample provides a concrete reference: 84 characters became a 5.17-second MP3 in about 4.7 seconds. Use the displayed character-based price to plan usage, and consider v4 Turbo when drafting or serving latency-sensitive flows. Publish text and voices you have the right to use, and never impersonate a real person.

ElevenLabs v4 API questions