Providers and Models ​

OSTT can use cloud providers or local Whisper-compatible models. Run ostt model to choose the active model. Run ostt auth login first when you want to use a cloud provider.

Transcription request params are configured under [provider.params] or [provider."model".params], or passed per invocation with --param key=value. Use ostt model params PROVIDER/MODEL to list supported params for a cloud or local model.

For practical recommendations by use case, see Choosing a Transcription Model or Provider.

Local ​

Local models run on your machine and do not require an API key. Open the local model manager with:

ostt model

Choose Local models to download curated models, activate downloaded models, delete model files, inspect metadata, or add a custom Hugging Face/direct model URL.

The curated model list is maintained in the kristoferlund/ostt-models repository. Open a pull request there to suggest a model for inclusion in the default list shown to all users.

Local transcription supports GPU acceleration through Metal on macOS and CUDA or Vulkan builds on Linux.

Local transcription requires WAV signed 16-bit PCM, 16 kHz, mono audio:

[audio]
output_format = "pcm_s16le -ar 16000"

Local Whisper params use the same provider/model format as cloud providers, for example [whisper.params], [whisper.turbo.params], or --param language=sv. Use model IDs such as whisper/turbo. See Local Models for setup details and local param descriptions.

Cloud Provider Guides ​

Landing Pages ​

These pages are broader introductions and workflow overviews:

• OpenAI Whisper CLI
• GPT-4o Transcribe on Linux
• Deepgram Nova 3 CLI
• Groq Whisper CLI
• AssemblyAI CLI on Linux
• ElevenLabs Transcription CLI
• Mistral Voxtral CLI
• Berget Whisper for Swedish
• Berget Whisper for Norwegian