Video-to-Text
Convert YouTube, TikTok and X videos to accurate transcripts with timestamps. Supports 99 languages with auto-detection.
- Video-to-Text
- Audio-to-Text
Whisper Large V3 CT2
Whisper Large V3 with word-level timestamps and speaker labels. 99 languages with auto-detection. Transcribes TikTok, YouTube, X, Twitch and Kick URLs, X Spaces, and direct video and audio uploads.
- Free tier available
- No subscriptions
- No credit card required
Sample Outputs
Real outputs generated with Whisper Large V3 CT2 on deAPI.
Transcription
"result": { "text": "Can AI be trusted? Who's going to hit the brakes if we need to? Being able to achieve really does benefit the majority of people. If it ends up taking almost all the jobs, then what does it mean to work? Wait a minute. Why do we have to have this stuff? If a machine can pretend to care better than I can actually care, how do we draw the line there? If we all had a voice in it? then I feel like it would be better. Could AI help people stop feeling misunderstood? Could AI help me build more connections in the community? Can AI help me be a better teacher, a better mom? Maybe it'll cure some great things, you know? Things that we're not even at the cusp of understanding yet. Will it create a group of people that ask more questions? What if we started... to be more human again. We don't want to lose the most beautiful parts of life.", "language": "en", "language_probability": 0.979, "ts_level": "segment", "diarization_available": true, "segments": [ { "start": 8.43, "end": 43.7, "text": "Can AI be trusted? Who's going to hit the brakes if we need to? Being able to achieve really does benefit the majori…"result": { "text": "Can AI be trusted? Who's going to hit the brakes if we need to? Being able to achieve really does benefit the majority of people. If it ends up taking almost all the jobs, then what does it mean to work? Wait a minute. Why do we have to have this stuff? If a machine can pretend to care better than I can actually care, how do we draw the line there? If we all had a voice in it? then I feel like it would be better. Could AI help people stop feeling misunderstood? Could AI help me build more connections in the community? Can AI help me be a better teacher, a better mom? Maybe it'll cure some great things, you know? Things that we're not even at the cusp of understanding yet. Will it create a group of people that ask more questions? What if we started... to be more human again. We don't want to lose the most beautiful parts of life.", "language": "en", "language_probability": 0.979, "ts_level": "segment", "diarization_available": true, "segments": [ { "start": 8.43, "end": 43.7, "text": "Can AI be trusted? Who's going to hit the brakes if we need to? Being able to achieve really does benefit the majority of people. If it ends up taking almost all the jobs, then what does it mean to work? Wait a minute. Why do we have to have this stuff? If a machine can pretend to care better than I can actually care, how do we draw the line there? If we all had a voice in it?", "avg_logprob": -0.054, "speaker": "SPEAKER_04" }, { "start": 43.7, "end": 74.06, "text": "then I feel like it would be better. Could AI help people stop feeling misunderstood? Could AI help me build more connections in the community? Can AI help me be a better teacher, a better mom? Maybe it'll cure some great things, you know? Things that we're not even at the cusp of understanding yet. Will it create a group of people that ask more questions? What if we started...", "avg_logprob": -0.0476, "speaker": "SPEAKER_04" }, { "start": 74.06, "end": 80.18, "text": "to be more human again. We don't want to lose the most beautiful parts of life.", "avg_logprob": -0.0336, "speaker": "SPEAKER_00" } ] }
Transcription
"result": { "text": "Can AI be trusted? Who's going to hit the brakes if we need to? Being able to achieve really does benefit the majority of people. If it ends up taking almost all the jobs, then what does it mean to work? Wait a minute. Why do we have to have this stuff? If a machine can pretend to care better than I can actually care, how do we draw the line there? If we all had a voice in it? then I feel like it would be better. Could AI help people stop feeling misunderstood? Could AI help me build more connections in the community? Can AI help me be a better teacher, a better mom? Maybe it'll cure some great things, you know? Things that we're not even at the cusp of understanding yet. Will it create a group of people that ask more questions? What if we started... to be more human again. We don't want to lose the most beautiful parts of life.", "language": "en", "language_probability": 0.979, "ts_level": "segment", "diarization_available": true, "segments": [ { "start": 8.43, "end": 43.7, "text": "Can AI be trusted? Who's going to hit the brakes if we need to? Being able to achieve really does benefit the majori…"result": { "text": "Can AI be trusted? Who's going to hit the brakes if we need to? Being able to achieve really does benefit the majority of people. If it ends up taking almost all the jobs, then what does it mean to work? Wait a minute. Why do we have to have this stuff? If a machine can pretend to care better than I can actually care, how do we draw the line there? If we all had a voice in it? then I feel like it would be better. Could AI help people stop feeling misunderstood? Could AI help me build more connections in the community? Can AI help me be a better teacher, a better mom? Maybe it'll cure some great things, you know? Things that we're not even at the cusp of understanding yet. Will it create a group of people that ask more questions? What if we started... to be more human again. We don't want to lose the most beautiful parts of life.", "language": "en", "language_probability": 0.979, "ts_level": "segment", "diarization_available": true, "segments": [ { "start": 8.43, "end": 43.7, "text": "Can AI be trusted? Who's going to hit the brakes if we need to? Being able to achieve really does benefit the majority of people. If it ends up taking almost all the jobs, then what does it mean to work? Wait a minute. Why do we have to have this stuff? If a machine can pretend to care better than I can actually care, how do we draw the line there? If we all had a voice in it?", "avg_logprob": -0.054, "speaker": "SPEAKER_04" }, { "start": 43.7, "end": 74.06, "text": "then I feel like it would be better. Could AI help people stop feeling misunderstood? Could AI help me build more connections in the community? Can AI help me be a better teacher, a better mom? Maybe it'll cure some great things, you know? Things that we're not even at the cusp of understanding yet. Will it create a group of people that ask more questions? What if we started...", "avg_logprob": -0.0476, "speaker": "SPEAKER_04" }, { "start": 74.06, "end": 80.18, "text": "to be more human again. We don't want to lose the most beautiful parts of life.", "avg_logprob": -0.0336, "speaker": "SPEAKER_00" } ] }
Capabilities
What you can do with Whisper Large V3 CT2.
Audio-to-Text
Transcribe audio files and X Spaces into searchable text. Fast, multilingual, and perfect for content platforms.
Try nowHow to use in deAPI
Integrate Whisper Large V3 CT2 into your app with a single API call.
POST https://api.deapi.ai/api/v2/audio/transcriptions
curl · deAPI audio/transcriptions
curl -X 'POST' \ 'https://api.deapi.ai/api/v2/audio/transcriptions' \ -H 'accept: application/json' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "model": "WhisperLargeV3Ct2", "source_url": "https://www.tiktok.com/@claude/video/7660583650773323022", "include_ts": true }'{ "model": "WhisperLargeV3Ct2", "source_url": "https://www.tiktok.com/@claude/video/7660583650773323022", "include_ts": true }
Tip: The API returns a request_id. Use webhooks (recommended) or poll GET /jobs/{request_id} for results.
POST https://api.deapi.ai/api/v2/audio/transcriptions
curl · deAPI audio/transcriptions
curl -X 'POST' \ 'https://api.deapi.ai/api/v2/audio/transcriptions' \ -H 'accept: application/json' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -F 'model=WhisperLargeV3Ct2' \ -F 'source_file=@/path/to/file' \ -F 'include_ts=1'{ "model": "WhisperLargeV3Ct2", "source_file": "@/path/to/audio.mp3", "include_ts": true }
Tip: The API returns a request_id. Use webhooks (recommended) or poll GET /jobs/{request_id} for results.
Need an API key?
Sign up for free and get $5 in credits to start.
Similar Models
Other models with similar capabilities you might find useful.
Frequently Asked Questions
Whisper Large V3 with word-level timestamps and speaker labels. 99 languages with auto-detection. Transcribes TikTok, YouTube, X, Twitch and Kick URLs, X Spaces, and direct video and audio uploads.
Whisper Large V3 times the transcript by segment only. Whisper Large V3 CT2 adds word-level timestamps and speaker diarization, and always returns JSON with the detected language and its probability, plus a confidence score for each segment when you ask for timestamps.
TikTok, YouTube, X (Twitter), Twitch and Kick videos and X Spaces by URL, plus directly uploaded audio and video files. Uploads take AAC, MP3, OGG, WAV, WebM and FLAC audio up to 20 MB, and MP4, MPEG, MOV, AVI, WMV and OGG video up to 50 MB.
Send `"include_ts": true` with `"ts_level": "word"`. Each segment then carries a `words` list in which every word has its own `start` and `end` time in seconds. Without `ts_level`, timestamps are per segment.
Send `"diarize": true`. Each timed unit gets an anonymous label such as `SPEAKER_00` or `SPEAKER_01`; the labels tell voices apart within one file, not who the people are. Use it together with `"ts_level": "word"`: then every word carries its speaker and you can rebuild the conversation turn by turn. At segment level a segment can run up to about 30 seconds and get a single label even when several people speak in it.
Yes. Add `"include_metadata": true` and the result also carries the source's title, channel and engagement counts such as views and likes. It costs $0.005 per request and applies only to URL sources; uploaded files are never charged for it.
Yes. Whisper Large V3 CT2 is available via the deAPI REST API. Submit a request with `"model": "WhisperLargeV3Ct2"`, receive a request ID, and get the result by webhook or by polling. See the API documentation at https://docs.deapi.ai for code examples in Python, Node.js, and cURL.
- No subscription
- No credit card required
- Pay only for what you use
Try Whisper Large V3 CT2 — $5 for free
Get $5 in free credits and start generating with Whisper Large V3 CT2.