TRILL Audio Embedding
TRILL Audio Embedding is Google's speech to text model. An audio embedding model based on the TRILL (Triplet Loss network for Representation of Independently-collected Longitudinal data) architecture, designed for non-semantic audio classification tasks.
google-trill-audio-embedding |
| Speech to Text |
| Active |
| Google |
| Audio |
| Text |
Capabilities
Input1/5
Text·
Image·
Audio✓
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| TRILL Audio Embedding | — | — | — | — | Current |
| TRILL Distilled | — | — | — | — | Available |