Speech-to-Text Models
Transcription with timestamps, priced per second of audio.
- ElevenLabs Scribe V2$0.6012/ audio hr
ElevenLabs Scribe V2 is ElevenLabs’ speech-to-text model, built for accurate transcription across many languages. It accepts a language hint and returns word-level timestamps with speaker labels.
Anonymized - Parakeet ASR$0.36/ audio hr
Parakeet TDT 0.6B v3 is NVIDIA’s open-weight speech recognition model, with 600 million parameters and support for 25 European languages, which it detects on its own. It transcribes quickly, with punctuation and capitalization.
Private - Whisper Large V3$0.36/ audio hr
Whisper Large V3 is OpenAI’s open-weight speech recognition model, trained on about 5 million hours of audio and able to transcribe around 100 languages. It’s a robust general-purpose choice for multilingual transcription.
Private - Wizper (Whisper v3)$0.36/ audio hr
Wizper is an optimized deployment of OpenAI’s Whisper Large V3, transcribing the same languages with faster turnaround. It accepts a language hint and returns segment timestamps.
Private - xAI Speech to Text v1$0.1133/ audio hr
xAI Speech to Text v1 is xAI’s speech recognition model, which transcribes recorded audio into text. It accepts a language hint and returns word-level timestamps.
Private
Usage
Speech-to-text models transcribe spoken audio into written text. They are accessed via the Audio Transcriptions API.Supported audio formats
wav, wave, flac, m4a, aac, mp4, mp3, ogg, oga, webmA file is accepted when either its MIME type or its extension is on this list, and it must also pass a magic-byte check on the uploaded bytes. Renaming a file to a supported extension is not sufficient.Response formats
Timestamps
Settimestamps: true to receive timing data alongside the transcript. The response adds a timestamps object whose granularity depends on the model:{ "word": "...", "start": 0.0, "end": 0.5 } and segment entries are { "text": "...", "start": 0.0, "end": 3.2 }, with all times in seconds.