en-US.
wss://api.telnyx.com/v2/speech-to-text/transcription?language=es
Auto-Detection
Passmulti to enable automatic language detection. The aliases auto and auto_detect are silently mapped to multi.
?language=multi
?language=auto # → multi
?language=auto_detect # → multi
Engine Support
| Engine | Behavior |
|---|---|
| Deepgram | BCP-47 codes. multi for multi-language mode. |
| Telnyx | Whisper-based. auto_detect disables language hint entirely. |
| BCP-47 codes. | |
| Azure | BCP-47 codes. |
| xAI | Language codes such as en, fr, de, and ja. |
| AssemblyAI | Automatic multilingual detection and code switching across supported languages. |
| Speechmatics | Language codes such as en, es. Bilingual packs use Telnyx shorthand (e.g. ar_en) — mapped internally. Does not support auto; defaults to en if unrecognized. |
| Soniox | Automatic language detection. The language parameter is ignored — Soniox detects the language from the audio stream. |
| Parakeet | Automatic multilingual detection. The language parameter is ignored — Parakeet always auto-detects. omi-health/omi-med-stt-v1 is English-only. |
| Cohere | Only ar or en. Does not auto-detect — rejects auto (and multi) as an invalid value. Defaults to ar if omitted. |
| Reson8 | Supports 10 languages; can also accept auto (the default when omitted) for automatic language detection at the cost of transcription speed. |
| Humain | ar, en, codeswitch (Arabic/English code-switching), or auto (resolves to code-switching). Set en explicitly for English-only audio. |
Supported Languages
For most engines, Telnyx passes the language code directly without validation. The supported set depends on which engine you use. Speechmatics is the exception — Telnyx accepts shorthand codes for bilingual/multilingual packs and maps them to the provider’slanguage + domain configuration internally.
| Engine | Languages | Reference |
|---|---|---|
| Deepgram | 40+ languages across Deepgram models. Nova-3 supports multi (10 languages in code-switching mode). Flux is English-only; Flux-multi supports English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch, plus auto. | Deepgram languages |
| Telnyx | Whisper-based. 50+ languages. auto_detect to skip language hint. | — |
| 125+ languages/locales. | Google Cloud STT languages | |
| Azure | 100+ languages/locales. | Azure Speech languages |
| xAI | 25 languages, including Arabic, English, French, German, Hindi, Japanese, Korean, Portuguese, Spanish, and Vietnamese. | xAI Voice API |
| AssemblyAI | 18 languages with native multilingual code switching: English, Spanish, German, French, Portuguese, Italian, Turkish, Dutch, Swedish, Norwegian, Danish, Finnish, Hindi, Vietnamese, Arabic, Hebrew, Japanese, and Mandarin (backed by Universal-3.5 Pro Realtime). | AssemblyAI supported languages |
| Speechmatics | 17+ languages. Standard codes (en, es, cy, sw, etc.) plus Telnyx shorthand for bilingual/multilingual packs (ar_en, cmn_en, en_ms, en_ta, cmn_en_ms_ta). Telnyx maps these internally to Speechmatics language + domain params — do not pass them raw to the provider. | Speechmatics languages |
| Soniox | Automatic language detection — no language hint required. The language parameter is ignored. | Soniox docs |
| Parakeet | Automatic multilingual detection — no language hint required. The language parameter is ignored. omi-health/omi-med-stt-v1 is English-only. | — |
| Cohere | ar and en only — no auto-detect. Defaults to ar if omitted. | — |
| Reson8 | 10 languages: nl, en, fr, fy, de, it, pl, pt, es, sv. Can also accept auto for automatic detection at the cost of transcription speed. | — |
| Humain | Arabic and English: ar, en, codeswitch, or auto. | - |
Common Codes
| Code | Language |
|---|---|
en or en-US | English (US) |
en-GB | English (UK) |
es | Spanish |
fr | French |
de | German |
pt-BR | Portuguese (Brazil) |
it | Italian |
ja | Japanese |
zh | Chinese (Mandarin) |
hi | Hindi |
ar | Arabic |
ko | Korean |
multi | Multi-language / auto-detect (Deepgram) |