Google speech-to-text service (full featured, v1-api)
Opensource version and examples |
Manual
OpenAI speech-to-text service (full featured, v1-api)
Opensource version and examples |
Manual
Feature | Commercial |
---|---|
Supported audio channels | * |
Voice activity detection (Advanced VAD) | + |
Voice features extraction ( ivectors ) | + |
Auto gain control (AGC) | + |
Speech start timeout timer | + |
Results in json with extra info (audio chunk, duration, etc) | + |
Returning service errors | + |
Keeping audio chunks | + |
Source code | - |
Price | $950 |
Feature | Opensource | Commercial |
---|---|---|
Supported audio channels | 1 | * |
Voice activity detection (VAD) | + | + |
Auto gain control (AGC) | - | + |
Speech start timeout timer | - | + |
Results in json with extra info (audio chunk, duration, etc) | - | + |
Returning service errors | - | + |
Keeping audio chunks | - | + |
Voice features protection (complicates speaker identification) | - | - |
Flexible HTTP settings (proxy/timeouts/etc...) | + | + |
Source code | + | - |
Price | free | $250 |
Feature | Opensource | Commercial |
---|---|---|
Supported audio channels | 1 | * |
Voice activity detection (VAD) | + | + |
Auto gain control (AGC) | - | + |
Flexible HTTP settings (proxy/timeouts/etc...) | + | + |
Speech start timeout timer | - | + |
Results in json with extra info (audio chunk, duration, etc) | - | + |
Returning service errors | - | + |
Keeping audio chunks | - | + |
Voice features protection (complicates speaker identification) | - | - |
Flexible HTTP settings (proxy/timeouts/etc...) | + | + |
Source code | + | - |
Price | free | $250 |