Widget de transcrición incrustábel

Engada voz a texto ao seu sitio web cunha liña de código. Envíe, URL e transcrición en directo, todo nun simple engadido.

Botón de incorporación da transcrición

Engade un botón de transcrición ao teu sitio web cunha liña de código. Cando se preme, abre unha xanela emerxente coa ferramenta completa de transcrición STT.ai.

Vista previa:

Widget completo incorporado

Para un widget completo en liña no canto dun botón, use a incorporación iframe de embaixo.

Demostración en directo

Código de incrustación

Copie e apegue este código no seu sitio web para engadir o widget de transcrición.

Obteña a súa chave da API na páxina da súa conta. Sen unha chave, aplicaranse límites de velocidade anónimos.

Eventos de JavaScript

Escoitar os eventos de transcrición do widget empregando eventos personalizados no elemento de contedor.

var widget = document.getElementById('stt-widget');

// Fired when a transcription completes
widget.addEventListener('stt:transcription', function(e) {
  console.log('Transcript:', e.detail.text);
  console.log('Source:', e.detail.source); // 'upload', 'url', or 'live'
});

// Fired on live transcription text
widget.addEventListener('stt:live-text', function(e) {
  console.log('Live text:', e.detail.text);
});

// Fired on errors
widget.addEventListener('stt:error', function(e) {
  console.log('Error:', e.detail.message);
});

Prezos dos widgets

Libre
$0/mo
  • Enviar, URL e transcrición en directo
  • 10 minutos libres/ día (anónimo)
  • Marca "Powered by STT.ai"
  • Soporta máis de 100 idiomas
White- Label
$19/mo
  • Todo en Libre
  • Eliminar a marca « Powered by STT.ai »
  • 7. 500 minutos/ mes (Plan Pro)
  • Soporte de temas personalizados
Obter o plan Pro

Propiedades do widget

Enviar o ficheiro
Arrastre e solte ou prema para enviar ficheiros de son/vídeo
Transcrición de URL
Apegue un URL de YouTube, Vimeo e máis de 1300 plataformas
Transcrición en directo
Fala en tempo real a texto desde o micrófono

Preguntas frecuentes

transcription widget runs in your browser: paste a URL, upload a file, or record from your mic. STT.ai picks the AI model and returns the transcript in under 5 minutes. Export as TXT, SRT, VTT, DOCX, JSON, or PDF.

Yes — every visitor gets 600 free minutes/month on STT.ai, usable for transcription widget the same as any other workflow. Paid plans starting at $5/month unlock longer files, private transcripts, and priority queueing.

transcription widget runs on the same AI models as the rest of STT.ai — our best models reach 95-97% accuracy on clean speech (3-5% Word Error Rate on benchmarks). Switch models on the fly if the first pass is below your target.

transcription widget can run on any of STT.ai's 10+ models — STT.ai Enhanced (most accurate), Whisper Large V3 (99 languages), NVIDIA Canary (#1 WER on supported langs), Whisper Turbo (fast), Moonshine (lightweight), and more.

Yes. Every transcript exports as SRT or VTT — works with YouTube, Vimeo, TikTok, VLC, and every major video player. The burn-subtitles tool overlays them onto video as hardsubs.

Yes. Speaker diarization automatically labels each voice (Speaker 1, Speaker 2, ...) and you can rename them in the built-in editor. Works across all models and languages.

Most transcription widget jobs finish in under 5 minutes. A 1-hour audio file typically completes in 2-3 minutes with our fastest models. Speed depends on chosen model and current GPU load.

transcription widget accepts 20+ formats — MP3, WAV, M4A, FLAC, OGG, MP4, MKV, MOV, WebM, AVI, and more. Output to TXT, SRT, VTT, DOCX, JSON, or PDF.

Yes. Audio files submitted to transcription widget are processed and deleted by default. Pro plans add client-side encryption — even if STT.ai's database is breached, your transcripts are unreadable without your key. Data is never used for model training without explicit opt-in.

Yes. STT.ai offers a REST API with Python and Node.js SDKs, plus an MCP server for Claude and Cursor — all usable for transcription widget workflows. Free API tier includes 100 minutes/month.

Yes. Every transcript opens in the built-in editor where you can correct words, rename speakers, adjust timestamps, and add notes. All changes save automatically.

Every transcript gets a unique shareable URL. Export to DOCX or PDF for email. Pro plans add password-protected and permanent links — useful for client work.

STT.ai handles 1,300+ platforms including YouTube, Vimeo, TikTok, SoundCloud, Zoom, Google Meet, podcast hosts, and more. URL transcription works with publicly-available content only — DRM-protected sources can't be transcribed.