How to build with Gemini 3.5 Transcribe
Summary
Google DeepMind launched Gemini 3.5 Transcribe, an LLM-based transcription model available via both the Interactions API and the Live API. This model significantly enhances accuracy by correctly transcribing complex data types—such as email addresses, phone numbers, and mixed units of measurement—and maintaining high performance across over 85 supported languages, even when language codes are set to English.
Key takeaways
-
LLM-Based Transcription Model
The model's LLM foundation allows it to handle complex data structures and context better than traditional transcription models. For example, it can correctly identify and edit email addresses even if spoken phonetically (e.g., 'tosten at google.com').
-
Handling Complex Data Types
2:00
Gemini 3.5 Transcribe accurately recognizes specific formats, including US phone numbers and international variations (e.g., Singapore's 8-digit format). It can also correctly interpret units of measure (e.g., meters vs. centimeters).
-
Multilingual and Customization Support
0:40
The model supports over 85 languages, automatically recognizing spoken language even if language hints are set to English. Accuracy can be further improved by providing custom vocabulary (e.g., names of people in a meeting) or setting specific language codes.
Technical details
-
Model Availability
0s
Gemini 3.5 Transcribe is available for both unary transcription via the Interactions API and real-time streaming via the Live API.
-
API Integration
175s
The model's deep understanding of language and reasoning capabilities make it suitable for new applications requiring highly accurate, real-time transcription.
Mentioned resources
- Google Developers
- Interactions API
- Live API
Channel & topics
Watch on YouTube · Back to latest
This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.