ElevenLabs
England, Vereinigtes KönigreichElevenLabs' realtime voice model with an OpenAI Realtime-compatible WebSocket API. It reasons before answering for complex instructions and multi-step tool use, supports Zero Retention Mode and HIPAA in the US and EU, and is available only in US and EU data residency environments.
ElevenLabs' realtime voice model with an OpenAI Realtime-compatible WebSocket API.
Eleven v4 is ElevenLabs’ most emotive text-to-speech model for narration, dialogue, and long-form audio in 90+ languages. Write expressive directions into the script: [warm] can set the tone of a greeting, [long pause] can build suspense, and [laughs], [whispers], or [door slams] can add reactions and sound effects at the right moment. The model follows sequences of audio tags, supports multiple speakers, and keeps delivery and voice consistent across longer recordings.
Eleven v4 Turbo brings v4’s expressive speech to real-time conversations and voice agents in 90+ languages. Inline cues such as [warm] for a welcome, [whispers] for a quiet aside, or [laughs] for a natural reaction help shape each turn. Built for streaming agent loops, it can start returning audio while text is still arriving, with about 100 ms median inference latency and about 150 ms median time to first speech. It maintains a consistent voice across long interactions.
Scribe V2 is a speech-to-text model from ElevenLabs for transcription and spoken-language understanding workflows. It is suited to captioning, meeting notes, transcription, and speech analytics pipelines.
Scribe V2 Realtime is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Speech recognition model fine-tuned for clinical audio, including medical terminology and dictation. Uses the Scribe speech-to-text API.
ElevenLabs Multilingual Speech to Speech V2 transforms speech while preserving delivery.
ElevenLabs Text to Sound V2 generates sound effects from text.
ElevenLabs Voice Dubbing translates audio while preserving speaker characteristics.
ElevenLabs Voice Isolation removes background noise and isolates speech.
Eleven English STS V2 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Eleven Flash V2 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation. It is tuned for lower latency and cost-sensitive production use.
Eleven Flash V2.5 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation. It is tuned for lower latency and cost-sensitive production use.
Eleven Multilingual STS V2 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Eleven Multilingual TTV V2 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Eleven Multilingual V2 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Eleven TTV V3 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Eleven Turbo V2 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation. It is tuned for lower latency and cost-sensitive production use.
Eleven Turbo V2.5 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation. It is tuned for lower latency and cost-sensitive production use.
Eleven V3 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Music is a music generation model from ElevenLabs for creating songs, instrumentals, and audio clips from prompts. It is aimed at prompt-driven soundtrack, jingle, and creative audio workflows.
Scribe V1 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Eleven Monolingual V1 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.
Eleven Multilingual V1 is a language model from ElevenLabs for chat, writing, analysis, and general-purpose automation.