News & Announcements
This document mainly introduces the latest updates on DolphinVoice platform's product features and related documentation.
20250918
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Audio File Transcription (Standard & VIP) | 1. VAD processing is also performed for stereo files. | Optimization |
| DolphinVoice | User Panel | 1. The project name and description can be modified after the project is created. | Addition |
20250814
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Hotwords | 1. When creating hotwords dictionary, you can customized the ID of it; 2. Optimize Japanese hotwords performance. | Addition Optimization |
20250701
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition Real-time Speech Recognition | 1. Add the function to return the confidence (reliability) of word information. | Addition |
20250627
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Real-time Speech Recognition | 1. Add the function of real-time speech recognition with role distinction. | Addition |
20250618
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition Real-time Speech Recognition | 1. Optimize modal particles matching rules; 2. Optimize Japanese word segmentation results; 3. API now includes pronunciations and dynamic sentence-breaking parameters. | Optimization Addition |
| Audio File Transcription (Standard & VIP) | 1. Optimize modal particles matching rules; 2. Optimize Japanese word segmentation results; 3. Optimize the segmentation logic for transcribing audio files. | Optimization |
20250606
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | General | 1. Adjust and optimize the upper limit of the number of hotwords supported by the Hothwords Database. | Optimization |
20250424
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition | 1. Add interface parameters to adjust the maximum audio duration for Short Speech Recognition. | Addition |
20250408
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Text to Speech | 1. Add the capability for Short Text to Speech. | Addition |
20250226
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition Real-time Speech Recognition Audio File Transcription (Standard & VIP) | 1. Add One-Time Hotwords Function; 2. Modify the default values of some parameters. | Addition Optimization |
| Hotwords | 1. Add API for creating, deleting, modifying, querying, and downloading hotwords; 2. For Japanese and Japanese-English mixed languages, hotwords are set in the form of hotword groups, with the structure of "writing, pronunciation, category". | Addition Optimization | |
| DolphinVoice | User Panel | 1. Optimized the hotwords registration process, supporting two registration methods: manual input and file upload; 2. Add display of hotwords related API addresses. | Optimization |
20250121
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition | 1. Adds the return of word information for HTTP interface. | Addition |
| Audio File Transcription (Standard & VIP) | 1. Change the audio duration limit to 5 hours; 2. Change the audio size limit to 1 GB. | Optimization | |
| DolphinVoice | General | 1. Enrichment of the homepage experience demo. 2. Optimize account registration experience. | Optimization |
20241226
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition | 1. Increase the confidence level of the return; 2. Optimize part of the logic. | Optimization |
| Real-time Speech Recognition Audio File Transcription (Standard & VIP) | 1. Increase the confidence level of the return. | Optimization |
20241127
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition Real-time Speech Recognition | 1. Support for forbidden word settings in Japanese and Japanese-English mixed languages; 2. Update Japanese-English mixed model files. | Optimization |
| Audio File Transcription | 1. Divide the audio file transcription service into Standard and VIP; 2. Optimize service performance; 3. Update Japanese-English mixed model files. | Optimization | |
| DolphinVoice | User Panel | 1. Add English version. | Addition |
20240926
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition Real-time Speech Recognition | 1. Updated Japanese, Japanese-English mixed, and Chinese-English mixed models to optimize recognition performance; 2. Add support for 8kHz audio recognition. | Optimization Addition |
| Audio File Transcription | 1. Updated Japanese, Japanese-English mixed, and Chinese-English mixed models to optimize recognition performance. | Optimization |
20240806
| Feature Type | Feature Name | Feature Description | Update Description |
|---|---|---|---|
| Speech Recognition | Short Speech Recognition | 1. Converts a short speech audio up to 60 seconds into text. | Initial Release |
| Real-time Speech Recognition | 1. Recognizes the streaming audio in real-time and returns the text results simultaneously. | Initial Release | |
| Audio File Transcription | 1. Converts audio files into text through batch processing and returns the text results. For a one-hour audio file, it is transcribed and the results are returned within 15 minutes. | Initial Release |
Platform Introduction
The DolphinVoice platform, based on Dolphin AI, K.K.'s proprietary speech recognition, speech synthesis, and other technologies, enables human-machine interaction experience. It can be effectively utilized in various business scenarios, such as meeting minutes, call center, medical documentation and e-commerce livestreaming.
Get Started
Next Page