Speech to Text
OpenAI Whisper with Video
Transcribe video audio with timestamps.
Hint: You can drag and drop a file or click to upload
Exemplo
Sample Transcription
{"text": "Loading sample transcription..."}Saída de exemplo mostrada acima. O prompt e as configurações estão preenchidos à esquerda.
Sua solicitação custará $0.000333 por execução. Por $10 você pode executar este modelo aproximadamente 30030 vezes.
Mais uma coisa:
Modelos Relacionados
README
OpenAI / OpenAI Whisper with Video — Speech to Text (openai-whisper-with-video)
OpenAI Whisper Large v3 Video-to-Text extracts audio from video files and provides accurate multilingual transcription with optional timestamped segments for subtitle creation.
Destaques
- •Direct video input – No need to extract audio separately.
- •Timestamp support – Get word-level timestamps for subtitles.
- •Multilingual – Supports 99+ languages with auto-detection.
- •Production ready – No cold starts, predictable pricing.
Parâmetros
- •video* – Video file to transcribe. Supports MP4, MOV, WebM, and AVI formats.
- •language – Language code (e.g., "en", "es", "fr"). Auto-detected if not specified.
- •timestamps – Include word-level timestamps for subtitle generation.
Precos
$0.004000 por geração
| Resolução | Preço |
|---|---|
| Per minute | $0.004 |
Como usar
- 1.Upload a video file (MP4, MOV, WebM, etc.).
- 2.Enable timestamps for subtitle-ready output.
- 3.Optionally specify the language code.
- 4.Receive transcription with optional timestamps.
Dicas Pro
- •Enable timestamps for subtitle generation workflows.
- •Works best with clear dialogue and minimal background music.
- •Auto language detection handles multilingual videos.
Mais modelos para experimentar
•Video subtitles: Generate SRT/VTT subtitle files.
•Content indexing: Make video content searchable.
•Accessibility: Add captions to video content.
•Video editing: Find specific moments by transcript.
Related Guides
Frequently Asked Questions
What is the OpenAI Whisper with Video API?
Transcribe video audio with timestamps.
How much does OpenAI Whisper with Video cost via API?
OpenAI Whisper with Video costs $0.0040 per generation through Renderful's API. No subscription required — pay only for what you use.
How do I use OpenAI Whisper with Video via API?
Sign up for a free Renderful API key, then send a POST request to the /v1/predictions endpoint with model "openai-whisper-with-video". See the documentation at renderful.ai/docs for code examples in Python, JavaScript, and cURL.
What type of content does OpenAI Whisper with Video generate?
OpenAI Whisper with Video is a speech to text model by OpenAI. Key features include: Video Input, Timestamps, Subtitle Segments.
Is the OpenAI Whisper with Video API fast?
OpenAI Whisper with Video has fast generation speed. Results are delivered via polling or webhook callback for seamless integration.