Transcribe an audio clip to text
One step with NVIDIA NIM. We can help you get access.
Get something done
Transcribe an audio clip to text
with NVIDIA NIM · Artificial Intelligence Management
Use NVIDIA NIM: its NVIDIA NIM Speech ASR API lets you transcribe an audio clip to text in a single step (POST /v1/audio/transcriptions). capabilities.work can help you get signed up and connected.
- Can I turn a WAV, FLAC or MP3 recording into text with a Parakeet or Canary speech model?
- Which language setting should I pass when transcribing a recording that isn't in English?
- What output formats can a speech-to-text transcription come back in?
Say it to your AI assistant
- Transcribe the audio file {file} to text using the {model} speech recognition model.
- Transcribe {file} with {model}, treating the spoken language as {language}.
- Get a transcript of {file} from {model} returned as {response_format}.
For your developer
POST /v1/audio/transcriptions in NVIDIA NIM Speech ASR API. Full spec on APIs.io.