Skip to main content
Every language your agent uses must be supported by both a voice (text-to-speech) provider and a speech recognition (ASR) provider. This page lists, for each language, which providers cover it.
The dashboard’s language picker is the live source of truth — it greys out combinations that aren’t supported and updates as providers add coverage. Use these tables for planning; confirm the exact combination in the dashboard. See Set language for your agent and Configure a multilingual agent for how selection works.
Codes are the values accepted by the API language field. Where a language has multiple locale variants (for example, US vs. British English), they share the same provider support.

Text-to-speech (voice) support

A ✓ means the language is supported by at least one of that provider’s voice models. Some providers gate certain languages to specific models — see Model-level restrictions below.
LanguageCode(s)PlatformMiniMaxFish AudioElevenLabsCartesiaOpenAI
Afrikaansaf-ZA
Arabicar-SA
Armenianhy-AM
Azerbaijaniaz-AZ
Bosnianbs-BA
Bulgarianbg-BG
Cantoneseyue-CN
Catalanca-ES
Chinesezh-CN
Croatianhr-HR
Czechcs-CZ
Danishda-DK
Dutchnl-NL, nl-BE
Englishen-US, en-IN, en-GB, en-AU, en-NZ
Filipinofil-PH
Finnishfi-FI
Frenchfr-FR, fr-CA
Galiciangl-ES
Germande-DE
Greekel-GR
Hebrewhe-IL
Hindihi-IN
Hungarianhu-HU
Icelandicis-IS
Indonesianid-ID
Italianit-IT
Japaneseja-JP
Kannadakn-IN
Kazakhkk-KZ
Koreanko-KR
Latvianlv-LV
Lithuanianlt-LT
Macedonianmk-MK
Malayms-MY
Marathimr-IN
Nepaline-NP
Norwegianno-NO
Persianfa-IR
Polishpl-PL
Portuguesept-PT, pt-BR
Romanianro-RO
Russianru-RU
Serbiansr-RS
Slovaksk-SK
Sloveniansl-SI
Spanishes-ES, es-419
Swahilisw-KE
Swedishsv-SE
Tamilta-IN
Thaith-TH
Turkishtr-TR
Ukrainianuk-UA
Urduur-IN
Vietnamesevi-VN
Welshcy-GB
Platform voices run on one or more of the other providers, but that routing is abstracted away — you don’t pick a provider, and Retell handles fallback automatically on an outage. For language selection, every platform voice shares the single fixed support set shown in the Platform column. A voice you clone as a platform voice is cloned onto several providers at once for automatic fallback. See Platform voices.

Model-level restrictions

Most providers support the same languages across all of their models. The exceptions: ElevenLabs
ModelLanguages
eleven_v3All languages in the ElevenLabs column above
eleven_flash_v2_5English, Japanese, Chinese, German, Hindi, French, Korean, Portuguese, Italian, Spanish, Indonesian, Dutch, Turkish, Filipino, Polish, Swedish, Bulgarian, Romanian, Arabic, Czech, Greek, Finnish, Croatian, Malay, Slovak, Danish, Tamil, Ukrainian, Russian, Hungarian, Norwegian, Vietnamese
eleven_multilingual_v2Same as eleven_flash_v2_5 above, minus Hungarian, Norwegian, and Vietnamese
eleven_flash_v2English only
Fish Audio
ModelLanguages
s2-pro, s2.1-proAll languages in the Fish Audio column above
s1English, Chinese, Japanese, German, French, Spanish, Korean, Arabic, Russian, Dutch, Italian, Polish, Portuguese
OpenAI (tts-1, gpt-4o-mini-tts), Cartesia (sonic-3, sonic-3-latest, sonic-3.5), and MiniMax (speech-02-turbo, speech-2.8-turbo) support their full language set on every model.

Speech recognition (ASR) support

A ✓ means the provider can transcribe that language. By default Retell auto-routes across providers based on your agent’s languages and whether it’s optimized for latency or accuracy. You can also pin a specific provider manually with a custom speech-to-text config, as long as it supports every language your agent uses. See Speech recognition providers.
LanguageCode(s)DeepgramAzureSonioxAssemblyAI
Afrikaansaf-ZA
Arabicar-SA
Armenianhy-AM
Azerbaijaniaz-AZ
Bosnianbs-BA
Bulgarianbg-BG
Cantoneseyue-CN
Catalanca-ES
Chinesezh-CN
Croatianhr-HR
Czechcs-CZ
Danishda-DK
Dutchnl-NL, nl-BE
Englishen-US, en-IN, en-GB, en-AU, en-NZ
Filipinofil-PH
Finnishfi-FI
Frenchfr-FR, fr-CA
Galiciangl-ES
Germande-DE
Greekel-GR
Hebrewhe-IL
Hindihi-IN
Hungarianhu-HU
Icelandicis-IS
Indonesianid-ID
Italianit-IT
Japaneseja-JP
Kannadakn-IN
Kazakhkk-KZ
Koreanko-KR
Latvianlv-LV
Lithuanianlt-LT
Macedonianmk-MK
Malayms-MY
Marathimr-IN
Nepaline-NP
Norwegianno-NO
Persianfa-IR
Polishpl-PL
Portuguesept-PT, pt-BR
Romanianro-RO
Russianru-RU
Serbiansr-RS
Slovaksk-SK
Sloveniansl-SI
Spanishes-ES, es-419
Swahilisw-KE
Swedishsv-SE
Tamilta-IN
Thaith-TH
Turkishtr-TR
Ukrainianuk-UA
Urduur-IN
Vietnamesevi-VN
Welshcy-GB
  • Azure covers every supported language and acts as the broad-coverage fallback.
  • AssemblyAI supports code-switching across its listed languages.
  • Deepgram and Soniox support any-to-any code-switching for multilingual agents across their supported languages; Azure is single-language only.

Multilingual agents

For a multilingual agent, every selected language must be covered by a single voice and a single ASR provider that can handle the whole set together. If no single provider covers the combination, the dashboard blocks it. See Configure a multilingual agent for accuracy trade-offs.