DeepLAudio modelActive
Aure
Summary
Aure is DeepL’s real-time speech translation model. It carries the speaker’s tone, pace, emphasis, and expression into translated speech. It supports English, German, Spanish, French, Italian, Japanese, Portuguese, and Korean.
DeepL makes Aure available automatically in DeepL Voice for online meetings, in-person conversations, and the Voice API. DeepL does not publish a separate API model ID, public weights, or a model license.
Similar models
More models of the same kind as Aure, chosen by model line, developer, size, price and release date.
- Live 3Fish Audio · released around the same time
- Scribe v3ElevenLabs · released around the same time
- Scribe v3 LiveElevenLabs · released around the same time
- Nemotron-3-DiarizationNVIDIA · released around the same time
- NVIDIA Nemotron 3.5 TranscribeNVIDIA · released around the same time
- MiniMax-Music3MiniMax · released around the same time
- Maya 2 NativeMaya Research · released around the same time
- Gemini 3.5 TranscribeGoogle · popular in this category
All specifications
Architecture
- Model type
- Proprietary real-time speech translation model that carries expression and speaking style into translated speech.
- Source: Model type
Input and output
- Languages
- English, German, Spanish, French, Italian, Japanese, Portuguese, and Korean. DeepL Voice continues to use its previous voice models for other languages.
- Source: Languages
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Unknown
- no source
- Watermarking technique
- Not known
- no source
Licence and access
- Access
- Automatically available in DeepL Voice for online meetings, in-person conversations, and the DeepL Voice API; no separate setup is required.
- Source: Access
- Shutdown
- None announced
- no source
API
- API model ID
- No separate API model ID has been published. Aure is used automatically in DeepL Voice for supported languages.
- Source: API model ID
Further details
- Voice transfer
- Continuously analyzes the source speech to reflect changes in tone, pace, emphasis, and expression in the translated voice. DeepL says it does not store a permanent voice profile.
- Source: Voice transfer
- Weights and license
- Proprietary hosted service. Public downloadable weights and a model license are not specified in the official Aure information.
- Source: Weights and license