{"slug": "nvidia-parakeet-stt-now-available-for-telnyx-voice-ai", "title": "NVIDIA Parakeet STT Now Available for Telnyx Voice AI", "summary": "NVIDIA Parakeet is now available as a speech-to-text engine for Telnyx Voice AI, enabling self-hosted multilingual transcription with automatic language detection for 25 European languages on Telnyx infrastructure. The engine, built on the nvidia/parakeet-tdt-0.6b-v3 model, requires no third-party API hop or language hint and supports linear16, linear32, mp3, or wav audio at 16 kHz, returning only final transcripts.", "body_md": "[Contact us](https://telnyx.com/contact-us)\n\n[Log in](https://portal.telnyx.com)\n\nNVIDIA Parakeet is now available as a speech-to-text engine for Telnyx Voice AI, bringing self-hosted multilingual transcription with automatic language detection to production voice workflows. Built on the `nvidia/parakeet-tdt-0.6b-v3`\n\nmodel, Parakeet transcribes 25 European languages on Telnyx infrastructure, with no third-party API hop and no language hint required.\n\n`language`\n\nparameter is required.`transcription_start`\n\n, TeXML `<Gather>`\n\nwith transcription, and the standalone TeXML `<Transcription>`\n\nverb. REST batch transcription is not available.`linear16`\n\n, `linear32`\n\n, `mp3`\n\n, or `wav`\n\naudio at 16 kHz.`nvidia/parakeet-v3`\n\n.For Call Control, POST to `transcription_start`\n\n:\n\n```\n{\n  \"transcription_engine\": \"Parakeet\",\n  \"transcription_engine_config\": {\n    \"transcription_engine\": \"Parakeet\",\n    \"transcription_model\": \"nvidia/parakeet-v3\"\n  }\n}\n```\n\nFor TeXML `<Gather>`\n\n:\n\n```\n<Gather transcriptionEngine=\"Parakeet\" model=\"nvidia/parakeet-v3\">\n  <Say>Please speak after the tone.</Say>\n</Gather>\n```\n\nFor WebSocket streaming:\n\n```\nwss://api.telnyx.com/v2/speech-to-text/transcription?transcription_engine=Parakeet&model=nvidia/parakeet-v3&input_format=linear16&sample_rate=16000\n```\n\nParakeet accepts `linear16`\n\n, `linear32`\n\n, `mp3`\n\n, or `wav`\n\naudio at 16 kHz and returns final transcripts only. No interim or partial results. Endpointing is ignored.\n\n**Learn more** in the [Speech-to-Text models docs](https://developers.telnyx.com/docs/voice/stt/models) or the [WebSocket streaming reference](https://developers.telnyx.com/docs/voice/stt/websocket-streaming/parameters).", "url": "https://wpnews.pro/news/nvidia-parakeet-stt-now-available-for-telnyx-voice-ai", "canonical_source": "https://telnyx.com/release-notes/nvidia-parakeet-stt-voice-ai", "published_at": "2026-07-17 00:00:00+00:00", "updated_at": "2026-07-17 19:36:21.021481+00:00", "lang": "en", "topics": ["artificial-intelligence", "natural-language-processing", "ai-products", "ai-infrastructure"], "entities": ["NVIDIA", "Telnyx", "Parakeet", "Telnyx Voice AI"], "alternates": {"html": "https://wpnews.pro/news/nvidia-parakeet-stt-now-available-for-telnyx-voice-ai", "markdown": "https://wpnews.pro/news/nvidia-parakeet-stt-now-available-for-telnyx-voice-ai.md", "text": "https://wpnews.pro/news/nvidia-parakeet-stt-now-available-for-telnyx-voice-ai.txt", "jsonld": "https://wpnews.pro/news/nvidia-parakeet-stt-now-available-for-telnyx-voice-ai.jsonld"}}