Skip to main content
ElevenLabs Documentation Docs

Search documentation

Type to search this documentation.

On this pageOverview

Text to Speech

Learn how to turn text into lifelike spoken audio with ElevenLabs.

ElevenLabs Text to Speech (TTS) API turns text into lifelike audio with nuanced intonation, pacing and emotional awareness. Our models adapt to textual cues across 32 languages and multiple voice styles and can be used to:

  • Narrate global media campaigns & ads
  • Produce audiobooks in multiple languages with complex emotional delivery
  • Stream real-time audio from text

Listen to a sample:

Explore our voice library to find the perfect voice for your project.

For real-time applications, Flash v2.5 provides ultra-low 75ms latency, while Multilingual v2 delivers the highest quality audio with more nuanced expression.

Explore all

ElevenLabs offers thousands of voices across 32 languages through multiple creation methods:

Learn more about our voice options.

Supported output formats

The default response format is mp3, but other formats like pcm and ulaw are available.

  • MP3
    • Sample rates: 22.05kHz - 44.1kHz
    • Bitrates: 32kbps - 192kbps
    • 22.05kHz @ 32kbps
    • 44.1kHz @ 32kbps, 64kbps, 96kbps, 128kbps, 192kbps
  • PCM (S16LE)
    • Sample rates: 16kHz - 44.1kHz
    • Bitrates: 8kHz, 16kHz, 22.05kHz, 24kHz, 44.1kHz, 48kHz
    • 16-bit depth
  • μ-law
    • 8kHz sample rate
    • Optimized for telephony applications
  • A-law
    • 8kHz sample rate
    • Optimized for telephony applications
  • Opus
    • Sample rate: 48kHz
    • Bitrates: 32kbps - 192kbps

Our multilingual v2 models support 29 languages:

English (USA, UK, Australia, Canada), Japanese, Chinese, German, Hindi, French (France, Canada), Korean, Portuguese (Brazil, Portugal), Italian, Spanish (Spain, Mexico), Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic (Saudi Arabia, UAE), Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, Ukrainian & Russian.

Flash v2.5 supports 32 languages - all languages from v2 models plus:

Hungarian, Norwegian & Vietnamese

Simply input text in any of our supported languages and select a matching voice from our voice library. For the most natural results, choose a voice with an accent that matches your target language and region.

The models interpret emotional context directly from the text input. For example, adding descriptive text like “she said excitedly” or using exclamation marks will influence the speech emotion. Voice settings like Stability and Similarity help control the consistency, while the underlying emotion comes from textual cues.

Read the prompting guide for more details.

Can I clone my own voice?

Yes, you can create instant voice clones of your own voice from short audio clips. For high-fidelity clones, check out our professional voice cloning feature.

Do I own the audio output?

Yes. You retain ownership of any audio you generate. However, commercial usage rights are only available with paid plans. With a paid subscription, you may use generated audio for commercial purposes and monetize the outputs if you own the IP rights to the input content.

What qualifies as a free regeneration?

A free regeneration allows you to regenerate the same text to speech content without additional cost, subject to these conditions:

  • You can regenerate each piece of content up to 2 times for free
  • The content must be exactly the same as the previous generation. Any changes to the text, voice settings, or other parameters will require a new, paid generation

Free regenerations are useful in case there is a slight distortion in the audio output. According to ElevenLabs’ internal benchmarks, regenerations will solve roughly half of issues with quality, with remaining issues usually due to poor training data.

How do I reduce latency for real-time cases?

Use the low-latency Flash models (Flash v2 or v2.5) optimized for near real-time conversational or interactive scenarios. See our latency optimization guide for more details.

Why is my output sometimes inconsistent?

The models are nondeterministic. For consistency, use the optional seed parameter, though subtle differences may still occur.

What's the best practice for large text conversions?

Split long text into segments and use streaming for real-time playback and efficient processing. To maintain natural prosody flow between chunks, include previous/next text or previous/next request id parameters.

  • Determinism: Output is nondeterministic — use the seed parameter for more consistent results
  • Free regenerations: Up to 2 free regenerations per generation (same content and parameters only)
  • Ownership: You retain ownership of generated audio; commercial use requires a paid plan
  • Low-latency use cases: Use Flash models (eleven_flash_v2 or eleven_flash_v2_5) — see the latency optimization guide
  • Large text: Split long text into segments; use the previous_text / next_text parameters to maintain natural prosody across chunks
Suggest an edit

Propose a replacement for this page. The site team reviews it before applying any changes.

Export
Documentation menu