Skip to main content
PTHub
PTHUB V-STT

Convert Speech Into
Intelligent Text

Fully automate transcribing meetings, interviews, and lectures. Convert 1 hour of audio into a complete transcript in just 3 minutes.

Vietnamese optimized VIAudio file processing BatchRegional dialects recognition 3 dialects

Trusted by 10,000+ leading creators and enterprises

VTV
Vietnam Television
FPT Software
FPT Group
Vietcetera
Podcast Network
VCCI
Vietnam Chamber of Commerce
Vingroup
Enterprise Group
Sconnect
Media Agency
KEY VALUES

Why Choose PTHub V-STT?

Ultra Fast

Streamline processing time

Automate meeting and interview notes while keeping transcripts reviewable and editable.

LLM Powered

Smart Search & Analytics

Turn static audio files into dynamic database. Easily search keywords, translate, and summarize with LLM.

Multi-dialect

Break Language Barriers

Support Northern, Central, and Southern dialects. Automated smart punctuation and spell checking.

Show, Don't Tell

Experience the power of AI in your browser

Record live speech, upload an audio file, or paste a podcast link to see instant transcription and speaker separation.

SYSTEM CAPABILITIES

Advanced AI Technology

Cross-platform & Real-time Sync

Use seamlessly on Web, iOS, Android, and Windows. Synchronized instantly to secure cloud.

All Audio Formats Supported

Accept MP3, WAV, MP4, M4A, FLAC... Simple drag-and-drop file processing.

Speaker Diarization

Advanced algorithms automatically detect and label different speakers in chronological order.

Robust API & Webhook

Designed for developers. Integrate high-quality speech recognition into CRM/ERP under 10 lines of code.

Khởi động chỉ sau 30 giây

Ready to turn audio into a valuable digital asset?

Start with a sample file or discuss the right integration workflow with PTHub.

Contact usĐã kiểm chứng bởi 10,000+ người dùng
Specialized solutions

Solutions for Every Industry

Audience

Enterprise

Vấn đề / Nỗi đau

Waste hours writing meeting minutes, risk missing key decisions and assigned tasks.

Giải pháp của V-STT

V-STT ghi nhận âm thanh cuộc họp, tự động chia người nói và trích xuất ngay danh sách công việc (Action-items) bằng AI.

Tính năng cốt lõi
Biên bản họp tự động
Phân loại người nói
Trích xuất Action Items
★★★★★

"Từ ngày dùng V-STT, phòng ban chúng tôi tiết kiệm được ít nhất 5 tiếng mỗi tuần để soạn thảo báo cáo cuộc họp. AI tóm tắt cực kỳ sát nghĩa."

Nguyễn Minh Thư

Trưởng phòng Vận hành FPT Software

Service pricing

Flexible Pricing Plans

Choose the right plan for your operating scale, integration needs, and security requirements.

Thanh toán hàng thángThanh toán theo năm Tiết kiệm 20%

Starter

Perfect for exploring technology or basic audio conversion.

60 minutes of free translation per month
Core Vietnamese speech recognition
Export formats: TXT / SRT
Supports uploads under 20MB
Register Demo
Khuyên dùng

Pro

For content creators and translation professionals.

/tháng

*Thanh toán 9đ /tháng

10 hours of high-quality translation per month
Context-aware Vietnamese recognition
Speaker Diarization included
AI Summarization & Key points extraction
Export: Word, PDF, Excel, SRT
Register Demo

Enterprise

For corporate clients requiring private deployment.

Custom hours/unlimited translation time
On-premise / private cloud hosting
Full API & Webhook access
SLA 99.9% guarantee
Custom vocabulary fine-tuning
Contact Sales
For developers

Developer Documentation

Integrate V-STT API into your enterprise software easily.

Endpoints

POST/v1/transcribe

Upload an audio file or specify an input stream to receive a detailed timestamped transcript.

Request parameters (Body Form-Data)
filerequired
binary (MP3, WAV...)
diarizationoptional
boolean (default: false)
languageoptional
string ("vi", "en"...)

API authentication

Use the Authorization: Bearer YOUR_API_KEY. header. Create a secure API key in your account dashboard.

Code sample
curl -X POST "https://api.vstt.ai/v1/transcribe" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@/path/to/meeting.mp3" \
  -F "diarization=true" \
  -F "language=vi"
Frequently asked questions

Frequently Asked Questions

Contact

Convert Speech Into

Fully automate transcribing meetings, interviews, and lectures. Convert 1 hour of audio into a complete transcript in just 3 minutes.

Data security commitment

PTHub trial infrastructure and forms are designed for secure information handling, helping protect enterprise and public-sector data.