# Speech

## Automatic Speech Recognition (ASR)

Low Latency NVIDIA Nemotron Speech transcription models for your agentic AI workflows.

- [parakeet-tdt-0.6b](/nvidia/parakeet-tdt-0_6b.md)
- [nemotron-asr-streaming](/nvidia/nemotron-asr-streaming.md)
- [parakeet-1.1b-rnnt-multilingual-asr](/nvidia/parakeet-1_1b-rnnt-multilingual-asr.md)
- [parakeet-ctc-0.6b-zh-tw](/nvidia/parakeet-ctc-0_6b-zh-tw.md)
- [parakeet-tdt-0.6b-v2](/nvidia/parakeet-tdt-0_6b-v2.md)
- [parakeet-ctc-1.1b-asr](/nvidia/parakeet-ctc-1_1b-asr.md)
- [parakeet-ctc-0.6b-asr](/nvidia/parakeet-ctc-0_6b-asr.md)
- [canary-1b-asr](/nvidia/canary-1b-asr.md)
- [whisper-large-v3](/openai/whisper-large-v3.md)
- [parakeet-ctc-0.6b-vi](/nvidia/parakeet-ctc-0_6b-vi.md)
- [parakeet-ctc-0.6b-zh-cn](/nvidia/parakeet-ctc-0_6b-zh-cn.md)
- [parakeet-ctc-0.6b-es](/nvidia/parakeet-ctc-0_6b-es.md)

## Speech to Speech (S2S)

Ultra-low latency, end-to-end, full duplex models for real-time voice-to-voice interactions.

- [nemotron-voicechat](/nvidia/nemotron-voicechat.md)

## Convert Text to Speech (TTS)

Convert written text to spoken audio in multiple languages with NVIDIA Nemotron Speech models.

- [chatterbox-multilingual-tts](/resembleai/chatterbox-multilingual-tts.md)
- [magpie-tts-multilingual](/nvidia/magpie-tts-multilingual.md)
- [magpie-tts-zeroshot](/nvidia/magpie-tts-zeroshot.md)

## Neural Machine Translation (NMT) & Audio Speech Translation (AST)

Enable seamless multilingual global communication across dozens of languages with NVIDIA Nemotron Speech models.

- [riva-translate-4b-instruct-v1_1](/nvidia/riva-translate-4b-instruct-v1_1.md)
- [riva-translate-1.6b](/nvidia/riva-translate-1_6b.md)
- [canary-1b-asr](/nvidia/canary-1b-asr.md)
- [whisper-large-v3](/openai/whisper-large-v3.md)