> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# How to choose the right model

ElevenLabs offers a range of models optimised for different requirements. The right choice depends on your use case, latency requirements, and quality expectations. Refer to the [models reference](/docs/overview/models) for full specifications.

## By requirement

Use `eleven_v3`

The flagship model with the highest fidelity, richest emotional expression, and broadest language support.

Use Flash models (`eleven_flash_v2_5` or `eleven_flash_v2`)

Optimised for real-time applications with \~75ms latency.

Use `eleven_v3` or `eleven_flash_v2_5`

Both support a wide range of languages.

Use `eleven_flash_v2_5`

High-quality output with low latency — the best all-round choice.

## By use case

Use `eleven_v3`

Ideal for professional content, audiobooks, and video narration.

Use `eleven_flash_v2_5` or `eleven_flash_v2`

Use the 2.5 model for language support outside of English.

Optimised for real-time conversational applications.

Use `scribe_v2` for batch transcription or `scribe_v2_realtime` for real-time transcription.

State-of-the-art accuracy across 90+ languages with speaker diarisation and word-level timestamps.

Use `eleven_multilingual_sts_v2`

Specialised for Speech-to-Speech conversion.

## Next steps

View full model specifications, latency benchmarks, and feature comparisons.

Reduce time-to-first-audio with model selection, voice choice, and geographic routing.