Key settings
endpointing: silence detection before a transcript is finallanguage: always set explicitly, because auto-detection adds latencyencoding/sampling_rate: must match your telephony provider
provider and model values each takes, see Create Agent.
Next steps
Speech-to-text providers
Setup guides for every transcriber Bolna supports
Supported languages
Languages and codes you can configure
Choose an LLM
The next provider in the pipeline
Back to the decision guide
Compare all provider categories side by side