Nemo3-ASR-Streaming API
Nemo3-ASR-Streaming from nvidia is an audio service in the catalogue. Text to speech and speech recognition are different tasks; confirm the model’s task and supported audio format before integrating.
PreparingService type
Sale prices will appear after provider configuration is complete.
- API model ID
- di-nvidianemo3-asr-streaming-acefc62ee1
- Model developer
- nvidia
- Service type
- Audio
- Current availability
- Preparing
Model features
No additional gateway capabilities have been confirmed for this model.
What is Nemo3-ASR-Streaming?
Use the public identifier di-nvidianemo3-asr-streaming-acefc62ee1 for Nemo3-ASR-Streaming in ServerNet. The gateway uses this identifier to select the configured route; the developer is nvidia.
Where to use Nemo3-ASR-Streaming
- Check whether Nemo3-ASR-Streaming synthesizes speech or transcribes audio.
- Evaluate pronunciation or transcription quality with a representative sample.
- Check audio duration, output format and supported voices or languages for your application.
Model description
Original catalogue description in English. It describes the model; the gateway limits and availability on this page define what you can request here.
Nemotron Speech Streaming EN 0.6B is NVIDIA's 600M-parameter cache-aware FastConformer-RNNT model for low-latency English speech recognition. It transcribes audio as it arrives, with native punctuation and capitalization, by reusing cached encoder context instead of recomputing overlapping windows. DeepInfra serves it at 560 ms lookahead over a realtime WebSocket API compatible with OpenAI Realtime transcription, batching many concurrent streams on each GPU, for live captioning, voice agents and real-time speech-to-text.
How to evaluate this model
For Nemo3-ASR-Streaming, compare the accepted input format and billing basis with alternatives in the same operation.
Before you integrate
- Use a representative test set and check factual accuracy, format and failure cases.
- Keep the first request bounded. Follow the operation-specific example and its API scope.
- Record response time and usage in your own environment before setting a production budget.
Build your integration
Audio execution needs explicit text or file limits and a verified native endpoint. Use the documented route once it becomes available; a text chat request does not perform an audio task.
Inputs and service limits
Character, duration and generation limits differ between audio models. Voice conditioning and uploaded audio can add consumption. Supported languages and voices must come from the model’s confirmed contract.
Image, audio, video and other native services can use different billing units. A token tariff is not a valid substitute. Sale opens only after the execution path and bounded billing contract are verified.
Frequently asked questions
Is Nemo3-ASR-Streaming available through ServerNet?
Nemo3-ASR-Streaming is currently unavailable for API use. A catalogue listing does not activate billing or access. Choose an available related model or check this page again after the route is verified.
Which model ID and API endpoint should I use for Nemo3-ASR-Streaming?
This model needs a native execution route. A chat, embedding or reranking example would not execute the advertised task. Its public page remains a catalogue reference until the route and metering are ready.
How is Nemo3-ASR-Streaming usage charged?
Image, audio, video and other native services can use different billing units. A token tariff is not a valid substitute. Sale opens only after the execution path and bounded billing contract are verified.
What should I check before using Nemo3-ASR-Streaming in production?
Character, duration and generation limits differ between audio models. Voice conditioning and uploaded audio can add consumption. Supported languages and voices must come from the model’s confirmed contract.