Skip to main content

elevenlabs/v4-turbo/text-to-speech

ElevenLabs v4 Turbo converts a text script into single-voice audio using ElevenLabs' latency-focused speech model. Pick from 21 premade voices and collect the finished recording through the task response.

From $0.048/1,000 characters

Workbench

Input

Text to speech
122/10000
Provide the required spoken script, up to 10,000 characters. Put inline cues such as [whispers] at the relevant words and proofread the text before generating a larger batch. at least 1 characters · at most 10000 characters

122 characters

Choose one of the 21 premade voices; omitting the selection uses Roger. Audition Sarah, Daniel or Lily with the same short line rather than supplying a custom voice ID.
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 FOR ITERATION

Turn short scripts into expressive audio for app prompts, production drafts and multilingual releases.

Key numbers

Characters per request
10,000
Premade voice choices
21
Language code choices
91
Output format options
9

Before you spend

All modes

Use text and voices you have the right to use, and do not impersonate a real person. A seed supports controlled comparisons without guaranteeing identical audio; the reported completion time describes one test call.

Text to speech

Each request accepts up to 10,000 text characters and uses one of 21 premade voices. Custom voice IDs and multi-speaker dialogue input are not available on this endpoint yet; clone_strength does not affect the premade voices.

What it does

Measured task result

A short Sarah recording, with context

Our 75-character Turbo request returned a 3.40-second MP3 after about 7.6 seconds on November 13, 2026. The call used Sarah and mp3_44100_128; it provides a concrete integration reference without predicting other scripts or workloads.

Voice and language choices

Cast a prompt set from 21 voices

Roger is the default among 21 premade voices, with Sarah, Daniel and Lily as other examples. Pair a selected voice with auto language detection or one of 91 language codes, then audition the actual wording of each localized prompt.

Script direction

Put a delivery cue beside the words

Square-bracket tags such as [laughs] or [whispers] belong inside text. Our test used one tag, so judge the returned performance rather than assuming that a larger collection of directions has been validated.

Export selection

Choose from 9 output options

Output defaults to mp3_44100_128, and mp3_22050_32 is another available choice. Select a listed format that your player accepts, then keep that setting fixed while you compare script revisions.

Where it fits

  • App status messages

    Input "Your upload is ready. Open the preview to continue." with Sarah to obtain a spoken status cue for an app. Audition it in the actual screen flow before reusing the voice.

  • Product-demo drafts

    Submit "Choose a workspace, add your files, then open the preview." to generate a narration draft. Compare the returned audio with the demo timing before preparing a final take.

  • Course instructions

    Use "Pause the lesson and list three examples from your own project." as a short course-audio script. The result is a single-voice recording you can review alongside the exercise.

  • Localized release prompts

    Supply "Tu archivo está listo." with language es to create a Spanish app voice prompt. Prepare each translated script yourself and generate a separate recording for it.

  • Game character lines

    Write "[whispers] The gate is open. Follow the lanterns." to try a directed NPC line. Receive one voice performance, then listen for the cue and the clarity of the instruction.

Model reference

ElevenLabs v4 Turbo API reference

ElevenLabs v4 Turbo API specifications

Publisher
ElevenLabs
Model
Eleven v4 Turbo
Public API name
elevenlabs/v4-turbo/text-to-speech
Required input
text; up to 10,000 characters
Voice selection
21 premade voices; Roger by default
Language selection
auto or 91 language codes
Delivery controls
Inline square-bracket audio tags; stability; similarity_boost
Text normalization
text_normalization_mode: auto, on or off
Output selection
9 options; mp3_44100_128 by default
Voice scope
One premade voice per request; custom IDs and multi-speaker input unavailable
Billing basis
Characters in text
Measured Turbo call
75 characters; Sarah; 3.40-second MP3; about 7.6 seconds to finish

How to call the ElevenLabs v4 Turbo API

  1. Prepare a short spoken script

    Write the words in text, keeping the request within 10,000 characters. Place a cue such as [whispers] directly where its delivery should apply.

  2. Choose voice, language and format

    Select a premade voice such as Sarah and choose auto or the intended language code. Keep mp3_44100_128 for the default output or choose another listed format.

  3. Send the text-to-speech request

    POST /api/v1/jobs/createTask with {"model":"elevenlabs/v4-turbo/text-to-speech","input":{"text":"Your upload is ready.","voice_id":"Sarah"}} and your bearer authorization header.

  4. Collect and audition the audio

    Query /api/v1/jobs/recordInfo?taskId=YOUR_TASK_ID until state is succeeded, then download the asset URL. Check names, numbers and tone before recording the remaining scripts.

The short version

Build a small set of spoken prompts before generating a larger library with ElevenLabs v4 Turbo. Try Sarah on an app notice, add a bracketed cue to a character line and check the pronunciation of a product name with your chosen normalization mode. Save each script and its settings with the returned audio so later revisions have a reference. Compare v4 for final narration using the same material, and estimate usage from text characters at the price displayed here. Publish text and voices you have the right to use, without impersonating a real person.

ElevenLabs v4 Turbo API questions