Skip to main content

Documentation Index

Fetch the complete documentation index at: https://hyperwhisper.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

​
Where your audio goes

HyperWhisper supports three transcription paths, each with different privacy implications:
PathWhere audio goesWho’s responsible for training opt-out
Local models (Whisper, Parakeet)Never leaves your deviceYou — but it’s offline, so there’s nothing to opt out of
HyperWhisper CloudRouted through HyperWhisper to a backing provider (Grok STT, ElevenLabs, Deepgram, or Groq)HyperWhisper — we opt you out on every upstream provider
Your own API key (BYOK)Sent directly from your device to the providerYou — except Deepgram, where we opt out for you automatically
If you want zero risk of your audio being used for training, use local transcription. It’s offline and the audio physically never leaves your Mac or PC.

​
HyperWhisper Cloud

When you use HyperWhisper Cloud, we forward your audio to a backing speech-to-text provider, and your transcribed text to a backing LLM for post-processing. We don’t store your audio on HyperWhisper’s own servers — it’s processed in memory at the edge and discarded after the response is returned. We’ve opted you out of model training on every upstream provider we use. That means:
  • For providers that expose a per-request opt-out flag, we set it on every call we make on your behalf.
  • For providers that only expose an account-level toggle, we’ve turned it off on the HyperWhisper account that handles your requests.
So as a HyperWhisper Cloud user, you don’t need to do anything — your audio is excluded from training across the entire stack.

​
Your own API keys (BYOK)

When you configure your own API key in Settings → API Keys, your audio is sent directly from your device to that provider, using their account, on their terms.
You are usually responsible for your own opt-out when using your own API keys. HyperWhisper cannot toggle dashboard-level settings on accounts we don’t control. Each provider has its own default — some don’t train on API data, some do unless you opt out.

​
Deepgram BYOK — we opt out for you automatically

For Deepgram specifically, HyperWhisper does the work for you on both macOS and Windows: every direct Deepgram request the app sends includes mip_opt_out=true in the query string. You don’t need to change any setting on your Deepgram dashboard for this to take effect — it applies on a per-request basis. Verify it on a recent request in console.deepgram.com under Usage → Logs: the request detail should show mip_opt_out: true.

​
Other providers — quick reference

ProviderTrains on API data by default?How to opt out
GroqNo — inference data is not retained by defaultOptional: enable Zero Data Retention in console.groq.com → Data Controls. Source
Anthropic (Claude)No — commercial API inputs/outputs are not used for trainingNothing to do for default usage. Source
CerebrasNo — API content is not used to train or fine-tune modelsNothing to do. Source
OpenAINo (since March 2023) — API data is not used for training by defaultNothing to do; verify under platform.openai.com → Settings → Data Controls
xAI GrokNo — API inputs and outputs are not used for training by defaultNothing to do for default usage; verify in the xAI data controls if your use case is sensitive
Google GeminiFree tier (AI Studio): yes, paid API: noUse a paid API key, or change settings in aistudio.google.com
ElevenLabsRetention is enabled by default; Zero Retention Mode is enterprise-onlyContact ElevenLabs sales if your use case requires it
AssemblyAINo — by default; verify in their security & privacy pageNothing to do for default usage
Fireworks AI, MistralVerify directly on their dashboardsSee “Verifying any provider” below
This table reflects publicly stated policies as of when this page was written. Providers can change their terms — for any provider whose policy is critical to your use case, verify directly using the prompt below.

​
Verifying any provider

Provider data policies move around — pages get renamed, settings get redesigned. The most reliable check is to ask a current language model. Open ChatGPT, Claude, or any LLM with web access and paste: 
I use {PROVIDER}'s API. I want to make sure {PROVIDER} does NOT train
their models on the audio, transcripts, or text I send through the API.

Please:
1. Find the official page that explains their data policy for API customers.
2. Tell me the exact setting, header, query parameter, or form I need
   to use to opt out of training.
3. Link me directly to the page or dashboard setting.
4. Tell me whether opt-out is on or off by default for new API accounts.

Cite official sources only (the provider's own docs or trust center).

​
If you’ve already used a key without opting out

A few things you can do:
  1. Opt out now — most providers stop using future requests for training the moment you flip the setting, even if past requests were used.
  2. Request deletion — many providers honor data deletion requests for previously sent content. The same LLM prompt above can ask “how do I request deletion of past API data on {PROVIDER}?”
  3. Rotate the key — if you want a hard line in the sand, generate a new key on the provider’s dashboard and replace the old one in Settings → API Keys.

​
Summary

  • Local = nothing leaves your device.
  • HyperWhisper Cloud = we opt you out of model training on every upstream provider, both at the request level and the account level.
  • Your own API key = mostly your responsibility — except for Deepgram, which HyperWhisper auto-opts-out by adding mip_opt_out=true to every request the app sends.
Related documentation: