Parakeet TDT 0.6B v3 is NVIDIA's 600M-parameter multilingual speech-to-text model built on the FastConformer-TDT architecture. Trained on the Granary dataset (670,000+ hours of audio), it supports automatic language detection across all official EU languages and achieves a 6.34% average word error rate on the HuggingFace Open ASR Leaderboard. Returns transcribed text with punctuation and segment timestamps.
Modalities
Price
$0.0015per minute
Released
May 27, 2026
Create an API key from your OpenRouter dashboard and set it as an environment variable:
Use nvidia/parakeet-tdt-0.6b-v3 with the OpenRouter API:
OpenRouter provides a speech-to-text API that transcribes audio into text. Send base64-encoded audio with a model, and receive the transcribed text in JSON.
The generation ID is returned in the X-Generation-Id response header for tracking.
For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.
https://openrouter.ai/api/v1/audio/transcriptionsBearer $OPENROUTER_API_KEYapplication/jsonoptional — your site URL, for rankingsoptional — your site name, for rankingsnvidia/parakeet-tdt-0.6b-v3| Name | Type | Default | Description |
|---|---|---|---|
max_tokens | integer | — | This sets the upper limit for the number of tokens the model can generate in response. |
temperature | float | 1 | This setting influences the variety in the model's responses. |
top_p | float | 1 | This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. |
stop | array | — | Stop generation immediately if the model encounter any token specified in the stop array. |
frequency_penalty | float | 0 | This setting aims to control the repetition of tokens based on how often they appear in the input. |
presence_penalty | float | 0 | Adjusts how often the model repeats specific tokens already used in the input. |
top_k | integer | 0 | This limits the model's choice of tokens at each step, making it choose from a smaller set. |
repetition_penalty | float | 1 | Helps to reduce the repetition of tokens from the input. |
logit_bias | map | — | Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. |
min_p | float | 0 | Represents the minimum probability for a token to be considered, relative to the probability of the most likely token. |