ElevenLabs TTS Turbo v2.5 Text to Speech API

elevenlabs/tts/turbo-v2.5

ElevenLabs TTS Turbo v2.5 Text to Speech turns scripts into natural speech in 32 languages, with selectable voices and adjustable pacing. Tune voice similarity and stability to shape a consistent delivery across your narration.

View API docs

Input

TextRequired

189 / 40,000 characters

VoiceOptional

SpeedOptional

StabilityOptional

Similarity BoostOptional

StyleOptional

TimestampsOptional

Language CodeOptional

Apply Text NormalizationOptional

Previous TextOptional

Next TextOptional

Output

Explore more audio models

ElevenLabs V3 Text to Speech ElevenLabs Music Text to Music

Examples

Finding north in the night sky

今晚，我们先找到北斗七星，再从勺口两颗星的方向寻找北极星。它看起来并不耀眼，却能帮我们辨认北方。在黑暗中安静地等待片刻，你会发现，夜空远比第一眼看到的更丰富。

Two cups of tea

Hoy volví a la casa de mi abuela. En la cocina seguía el reloj de siempre, cinco minutos adelantado. Preparé dos tazas de té por costumbre y, al darme cuenta, sonreí. Algunos gestos también guardan recuerdos.

REST API

Quick Start

This flow submits one valid ElevenLabs TTS Turbo v2.5 Text to Speech API request, captures its task_id, and reads audio URLs after the asynchronous task ends.

Connect to the Vidgo API

Create an API key, keep it on the server, and send it as Authorization: Bearer VIDGO_API_KEY.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one speech task

Send the current model ID and text to the unified submit endpoint. The example keeps only first-call fields.

Submit request

curl --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "elevenlabs/tts/turbo-v2.5",
  "input": {
    "text": "Welcome. Your next chapter starts here.",
    "voice": "Rachel",
    "speed": 1,
    "stability": 0.5,
    "similarity_boost": 0.75,
    "style": 0,
    "timestamps": false,
    "apply_text_normalization": "auto"
  }
}'

Wait for the speech result

Read data.task_id and poll only while status is not_started or running. Stop on both finished and failed.

Track status

GET https://api.vidgo.ai/api/generate/status/{task_id}

Poll every 2–5 seconds and back off on 429/5xx. Or provide top-level callback_url to receive a terminal-state callback.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "task-example",
    "status": "running",
    "created_time": "2026-09-25T11:31:42"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "task-example",
    "status": "finished",
    "files": [
      {
        "file_url": "https://example.com/speech.mp3",
        "file_type": "audio"
      }
    ],
    "created_time": "2026-09-27T00:00:00",
    "progress": 100,
    "error_message": null
  }
}

Complete runnable polling example

Expand for JavaScript and Python examples that submit the same text request and poll until finished or failed.

Complete runnable polling example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "elevenlabs/tts/turbo-v2.5",
  "input": {
    "text": "Welcome. Your next chapter starts here.",
    "voice": "Rachel",
    "speed": 1,
    "stability": 0.5,
    "similarity_boost": 0.75,
    "style": 0,
    "timestamps": false,
    "apply_text_normalization": "auto"
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

while true; do
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep 2
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters

This table lists only public fields inside input. See Quick Start for top-level model and optional callback_url usage.

Field	Type	Required	Default	Description
input.text	string	Yes	–	Enter the script to read aloud. After trimming outer whitespace, each request accepts 1–40,000 Unicode characters.
input.voice	string	No	Rachel	Choose a voice name or a compatible voice ID. The default is Rachel.
input.speed	number	No	1	Set the speaking rate from 0.7 to 1.2. Use 1 for the standard pace.
input.stability	number	No	0.5	Set a value from 0 to 1. Higher values favor a steadier delivery; lower values allow more variation. Default: 0.5.
input.similarity_boost	number	No	0.75	Adjust similarity to the selected voice from 0 to 1. Default: 0.75.
input.style	number	No	0	Set style exaggeration from 0 to 1. Start at the default of 0, then audition small changes.
input.timestamps	boolean	No	false	Set true to request timestamp data alongside the audio. Default: false.
input.language_code	string \| null	No	–	Enter an ISO 639-1 language code, such as en, zh or es, to specify the language.
input.apply_text_normalization	string	No	auto	Choose auto, on or off to control normalization of numbers, dates and currencies. Default: auto.
input.previous_text	string \| null	No	–	Add the preceding passage to help guide delivery across separate requests.
input.next_text	string \| null	No	–	Add the following passage to provide context for the end of the current segment.

Response Fields

The submit response identifies the task. The status response supplies audio files or failure details at a terminal state.

Field	Type	Description
code	integer	Business response code; 0 or 200 indicates success.
message	string	Optional human-readable response message.
data.task_id	string	Unique task ID used for status queries after submission.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation timestamp.
data.progress	integer	Progress from 0–100 in status responses.
data.files[]	array	Generated files in returned order when finished.
data.files[].file_url	string	Direct generated-audio URL.
data.files[].file_type	string	Speech files are identified as audio.
data.files[].metadata	object	Preserve returned optional metadata and additional files, including timestamp data when present.
data.error_message	string \| null	Readable failure reason for failed tasks.

Task Lifecycle

Only the first two states may be polled again. finished and failed are terminal.

not_started
Accepted and queued; wait before checking again.
running
Speech generation is in progress; continue polling.
finished
Successful terminal state; validate files and read audio URLs.
failed
Failure terminal state; read error_message and stop.

Polling and Errors

Authentication401 indicates an authentication failure. Use a valid API key and send requests from your server.
ValidationFollow the request table for the model ID, field types, enums, text length, and numeric ranges.
Polling intervalStart at 2–5 seconds, use exponential backoff for 429/5xx, and enforce an overall timeout.
Terminal statesStop after finished or failed. Treat finished without a valid audio file as a separate error.
Callback optionProvide a public top-level callback_url to receive a flat task object after finished or failed.
Network errorsDistinguish request timeout, network failure, and task failure. Retry the same query only when safe.

Model Specifications

Specification	Value	Details
Model	elevenlabs/tts/turbo-v2.5	Text-to-speech generation.
text	1–40,000	Unicode characters after trimming leading and trailing whitespace.

ElevenLabs TTS Turbo v2.5 Text to Speech API documentation

ElevenLabs TTS Turbo v2.5 Text to Speech

ElevenLabs TTS Turbo v2.5 Text to Speech is an ElevenLabs model that balances natural voice quality with low latency for multilingual speech generation. It converts written scripts into spoken audio, using voice selection and adjustable delivery settings to shape the result. For tutorials, localized narration and spoken product messages, neighboring text can guide continuity when a longer script is split into segments.

Why choose ElevenLabs TTS Turbo v2.5?

One workflow for 32 languages.Create narration in English, Mandarin Chinese, Spanish and other supported languages, selecting a voice and language for each script.
Delivery you can shape.Choose a voice, adjust its speaking rate and balance stability with variation to suit a lesson, announcement or narrated scene.
Context for segmented narration.Provide the text before and after a passage to guide transitions while generating a longer script in separate requests.
Audio with timing data.Enable Timestamps when you need timing information alongside the generated speech for a subsequent editing workflow.

Parameters

Parameter	Required	What it controls
text	Required	Enter the script to read aloud. After trimming outer whitespace, each request accepts 1–40,000 Unicode characters. `1–40,000`
voice	Optional	Choose a voice name or a compatible voice ID. The default is Rachel. Default`Rachel`
speed	Optional	Set the speaking rate from 0.7 to 1.2. Use 1 for the standard pace. Default`10.7–1.2`
stability	Optional	Set a value from 0 to 1. Higher values favor a steadier delivery; lower values allow more variation. Default: 0.5. Default`0.50–1`
similarity_boost	Optional	Adjust similarity to the selected voice from 0 to 1. Default: 0.75. Default`0.750–1`
style	Optional	Set style exaggeration from 0 to 1. Start at the default of 0, then audition small changes. Default`00–1`
timestamps	Optional	Set true to request timestamp data alongside the audio. Default: false. Default`falsetrue`
language_code	Optional	Enter an ISO 639-1 language code, such as en, zh or es, to specify the language.
apply_text_normalization	Optional	Choose auto, on or off to control normalization of numbers, dates and currencies. Default: auto. Default`autoonoff`
previous_text	Optional	Add the preceding passage to help guide delivery across separate requests.
next_text	Optional	Add the following passage to provide context for the end of the current segment.

Create your first voiceover

Prepare the spoken script.Enter your narration in Text. Use sentences and punctuation to make the intended phrasing clear.
Choose the voice and delivery.Set Voice and Language Code, then adjust Speed, Stability and Similarity Boost. Start with a representative passage to audition the settings.
Review the estimate and select Run.Check the cost shown for your script. Sign in with sufficient credits, then select Run to submit the request.
Listen and download.When the audio is ready, preview it in Output and download the file. If you requested timestamps, inspect the returned files for timing data.

Usage and pricing

ElevenLabs TTS Turbo v2.5 Text to Speech costs 8 credits ($0.04) per 1,000 billable characters. Usage is calculated proportionally from Text after trimming leading and trailing whitespace.

Usage	Rate	Calculation
Speech generation	8 credits / 1,000 characters	Equivalent to $0.04 per 1,000 billable characters. A script with 500 billable characters costs 4 credits ($0.02).
Character counting	UTF-16 code units	A basic Latin letter or common Chinese character counts as one unit. An emoji such as 😀 counts as two. This billing count differs from the Unicode character count used for the 40,000-character input limit.

Where Turbo v2.5 fits

Localized video narration.Turn translated scripts into spoken tracks for product videos, explainers and audience-specific versions.
Lessons and tutorials.Adjust the pace of instructional narration and reuse a selected voice across individual lessons.
Spoken product messages.Generate welcome messages, guided instructions and announcements in the languages your audience uses.
Serialized narration.Produce chapter or scene segments with neighboring text to guide how each passage begins and ends.

Get more from your script

Audition the same short passage while changing one voice setting at a time, then use your chosen settings across the project.
For a steadier delivery, raise Stability; for more variation, lower it and listen to the passage again.
Split longer scripts at sentence or paragraph boundaries and provide Previous Text and Next Text for each segment.
For text containing dates, amounts or abbreviations, choose a normalization mode and listen to those phrases before generating the full script.
Use punctuation to guide phrasing, then adjust Speed to fit the pace of your lesson or narration.

Before you run

Enter the words to be spoken in Text. Use Previous Text and Next Text for surrounding context.
Use the same Voice and delivery settings across related segments, then listen to the joins when assembling the final track.
Review the character count and estimated charge after editing the script; they use different counting rules, explained in Usage and pricing.

Explore other ElevenLabs models

Gemini 3.1 Flash TTS Text to Speech preview

Gemini 3.1 Flash TTS Text to SpeechCreate multilingual narration and two-speaker dialogue with 30 voices, style instructions and expressive audio tags.

MiniMax Music 2.6 Text to AudioCreate songs and instrumentals from style prompts, with custom or automatic lyrics and configurable audio output.

Suno MusicAI music generator with customizable styles, vocals, and full creative control over musical characteristics and quality.

Extend MusicExtend or modify existing music tracks by creating sequels based on source audio. Supports custom mode with full parameter control or simple mode inheriting original parameters. Specify continuation points and maintain style consistency across extensions up to 8 minutes.

Upload and Cover AudioTransform audio tracks into new styles while preserving original melodies. Upload your audio files (up to 2 minutes) and convert them with AI-powered style transfer. Supports custom and simplified modes with vocal/instrumental options and audio weight controls.

Upload and Extend AudioUpload audio files and extend them while maintaining the original style and characteristics. AI generates seamless continuations from specified time points. Supports multiple model versions with style weight and creative controls for natural extensions.

Add InstrumentalGenerate musical accompaniment for uploaded audio files containing vocals or melodies. AI creates matching instrumental backing tracks with customizable style tags, genre preferences, and quality controls. Perfect for adding professional-quality backing to vocal recordings.

Add VocalsLayer AI-generated vocals onto existing instrumental tracks. Provide lyrics or descriptions and the API generates matching vocal performances with customizable gender, style, and expression. Transform instrumental music into complete songs with professional AI singing.

Get Timestamped LyricsRetrieve lyrics synchronized with precise timestamps from generated music. Returns word-by-word timing data, waveform visualization, and alignment accuracy scores. Essential for karaoke applications, lyric videos, and music synchronization projects.

Boost Music StyleAI-enhanced music style description generator. Transform simple style inputs like 'pop, mysterious' into detailed, comprehensive musical descriptions. Optimize your prompts for better music generation results with enriched genre, mood, and instrumentation details.

Generate Music CoverGenerate alternative cover versions of existing music tracks. Create variations with automatic style changes while maintaining the essence of the original composition. Perfect for producing multiple versions or exploring different interpretations of your generated music.

Replace SectionReplace specific sections of generated music tracks with precision timing control. Modify choruses, verses, or any segment by specifying start and end times. Maintains overall coherence while allowing targeted changes to lyrics, style, or musical elements.

Generate PersonaCreate reusable music personas from existing audio tracks. Save distinctive vocal characteristics, musical styles, and personality traits for consistent use across multiple generations. Build your own AI artist profiles for brand consistency and style continuity.

Generate LyricsAI-powered lyrics generation based on themes, moods, and descriptions. Create original song lyrics from simple prompts up to 200 characters. Generate creative, coherent lyrics for any genre or emotional tone with professional songwriting quality.

Convert to WAVObtain high-quality WAV format files from your generated music. Convert any PoYo-generated audio to lossless WAV format for professional use, further editing, or high-fidelity playback. Essential for production workflows requiring uncompressed audio.

Vocal RemoverSeparate vocals from instrumentals or split audio into multiple stem tracks. Two modes available: vocal separation for isolating vocals and backing tracks, or stem splitting for extracting drums, bass, vocals, and other instruments individually. Professional-grade audio source separation.

ElevenLabs TTS Turbo v2.5 Text to Speech API frequently asked questions

What is the ElevenLabs TTS Turbo v2.5 Text to Speech API?

ElevenLabs TTS Turbo v2.5 Text to Speech is an ElevenLabs model for turning written scripts into natural spoken audio with a focus on low latency. It supports 32 languages, selectable voices and adjustable speech delivery. Voice similarity, stability and surrounding text let you guide the sound and continuity of your narration. You can call it programmatically or try it from the playground above.

Does ElevenLabs Turbo v2.5 support Chinese speech?

Yes. Mandarin Chinese is one of the 32 supported languages, alongside English, Japanese, Spanish and others. Enter your Chinese script in Text and use zh for Language Code to specify Chinese.

Can ElevenLabs Turbo v2.5 read 40,000 characters?

Each request accepts 1–40,000 Unicode characters after leading and trailing whitespace is trimmed. For a longer narration project, split the script into passages and use Previous Text and Next Text to provide context around each one.

How do I choose a voice in ElevenLabs Turbo v2.5?

Set Voice to a voice name or a compatible voice ID. Rachel is the default. Audition a short passage in your target language, then adjust Similarity Boost to guide similarity to the selected voice.

How can I change the speaking speed in ElevenLabs Turbo v2.5?

Set Speed between 0.7 and 1.2, with 1 as the default. Values below 1 slow the speech down, while values above 1 increase the pace. Preview a representative passage before applying the setting to a longer script.

How does ElevenLabs Turbo v2.5 control expressiveness?

Use Stability to balance a steadier delivery with variation: higher values favor consistency and lower values allow more variation. Style controls style exaggeration. Both accept values from 0 to 1; start at Stability 0.5 and Style 0, then audition small changes.

How can ElevenLabs Turbo v2.5 connect narration segments?

Supply Previous Text and Next Text to give each passage its surrounding context. Keep Voice and delivery settings consistent across the project, split at natural sentence boundaries and listen to the joins when assembling the audio.

How does ElevenLabs Turbo v2.5 read numbers and dates?

Apply Text Normalization controls preparation of numbers, dates and currencies for speech. Choose auto for automatic handling, on to enable normalization or off to use the supplied text directly. Specify Language Code and preview a sample containing the values you need read aloud.