ElevenLabs model catalog
Current models I verified against the official docs overview. Names keep official spelling.
Eleven v3
Most expressive speech model: dramatic delivery, audio tags, 70+ languages, multi-speaker dialogue.
Eleven v3 Conversational
Realtime expressive speech for agents and interactive characters (~280ms model latency).
Eleven Multilingual v2
Lifelike, consistent TTS across 29 languages — strong for long-form narration stability.
Eleven Flash v2.5
Ultra-low latency TTS (~75ms) for conversational apps; 32 languages; leaner per-character cost.
Scribe v2
Speech recognition with word-level timestamps, diarization, entity detection, 90+ languages.
Scribe v2 Realtime
Streaming transcription with low latency (~150ms) for live captions and agent loops.
Eleven Music v2
Studio-grade music from natural-language prompts — vocals or instrumental, editable sections.
Independent catalog. Confirm limits on the official ElevenLabs website.