Add Soniox as an API speech-to-text option

This commit is contained in:
James Babcock committed 2026-08-04 20:15:39 -07:00
1 parent 852626e950
commit ba81e46624
9 files changed
+218 -14

No files matched your search

+3 -1
View File
@@ -11,7 +11,8 @@ on-device model is selected, audio never leaves your device, and is not stored
after it is processed.
Users can also provide their own API key for a third-party transcription
service such as OpenAI Whisper or ElevenLabs, which may offer better accuracy.
service such as OpenAI Whisper, ElevenLabs, or Soniox, which may offer better
accuracy.
Faceclaw never transmits audio to any party other than a user-selected
transcription service. If a third-party transcription service is selected,
audio will be sent to that third party, is linked to the account with which
@@ -20,6 +21,7 @@ policies:
OpenAI: https://openai.com/policies/row-privacy-policy/
ElevenLabs: https://elevenlabs.io/privacy-policy
Soniox: https://soniox.com/policies/privacy-policy
Third party data retention and privacy policies may differ based on the API
key provided. API keys are part of a relationship between the user and the API