Skip to main content
Retell automatically picks a speech recognition provider based on the languages your agent is configured for. You don’t need to choose one manually, but it helps to understand the trade-offs when deciding which languages to support.
These observations are based on our internal testing and routing rules. Results may vary depending on the specific languages, audio conditions, and call patterns.

​
Provider overview

​
Deepgram

  • Best for: Lowest latency, the default for single-language agents on common languages.
  • Multilingual: Supports code-switching across 10 languages: English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, Dutch.
  • Consideration: Doesn’t cover less-common languages (e.g., Welsh, Marathi, Kazakh).

​
Azure

  • Best for: The broadest single-language coverage — including languages no other provider supports (e.g., Icelandic, Nepali, Filipino).
  • Consideration: No multilingual mode. Used only when the agent is configured with a single language.

​
Soniox

  • Best for: Multilingual code-switching across a much wider set than Deepgram — about 50 languages, with the same coverage in both single and multi modes.
  • Consideration: Slightly higher latency than Deepgram, so Retell prefers Deepgram when both providers support a language.

​
How Retell picks a provider

Retell evaluates the agent’s selected languages against each provider’s coverage and routes to the most accurate option:
  • Single common language → Deepgram.
  • Single uncommon language (not covered by Deepgram) → Azure.
  • Multiple languages, all within Deepgram’s multilingual set → Deepgram multilingual.
  • Multiple languages, broader combination → Soniox.
  • Multiple variants of the same base language (e.g., en-US + en-GB) → routed as single-language for that base, with no accuracy penalty.
If no single provider can cover all of your selected languages together, the dashboard prevents you from selecting that combination. See Configure a multilingual agent for details.