Vietnamese speech-to-text API (Tiếng Việt)

Transcribe Vietnamese with one request

Set language to vi and start a job. Poll GET /transcribe/{jobId} for the result, or pass a webhook_url.

curl https://app.kolwrite.com/transcribe \
  -H "x-api-key: $KOLWRITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_url": "https://example.com/phong-van-vi.m4a", "model": "oracle", "language": "vi", "include_diarization": true, "output_format": "json"}'

Translate Vietnamese audio into English in the same job (Oracle models only):

curl https://app.kolwrite.com/transcribe \
  -H "x-api-key: $KOLWRITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_url": "https://example.com/phong-van-vi.m4a", "model": "oracle_mini", "language": "vi", "translate_to": "en", "output_format": "srt"}'

Vietnamese at a glance

What to know about Vietnamese transcription

• Vietnamese is tonal and its Latin script stacks diacritics (ế, ợ). Store text in Unicode NFC; mixing NFC and NFD breaks search and comparison.
• Northern, Central and Southern accents differ noticeably. There is no regional setting; test the regions you serve.
• Vietnamese words are written syllable by syllable with spaces, so word timestamps usually align to syllables.

Where teams use Vietnamese transcription

• Customer calls and sales for companies in Vietnam.
• Vietnamese video and e-learning subtitles.
• Interviews translated to English with translate_to: "en".

Choosing a model

Start with oracle (US$1.44 per hour) for production Vietnamese audio. Use base (US$0.48) for clean, single-speaker recordings at volume, oracle_mini (US$0.96) for the cheapest translation, and oracle_pro or oracle_max for noisy or difficult audio. KolWrite does not publish a Vietnamese accuracy figure for this API, so test a sample of your own recordings before committing. Full comparison: models and prices.

Questions and answers