Back: Catalog

Speech

NVIDIA NeMo Speech is a scalable Python framework that offers audio, speech and multi-mode AI models for researchers and developers. It includes open-weight checkpoints in areas such as automatic Konuşma Tanıma (ASR) and Metin Okuma (TTS). It supports distribution with NGC containers and HuggingFace integrations.

SP

Speech

100

NVIDIA-NeMo · Voice & Text-to-Speech

STARS18.7K
FORKS3.7K
COMMITS9.6K
CONTRIBUTORS400
VERSIONv3.0.0
UPDATEDtoday
PythonKonuşma TanımaMetin OkumaAIApache-2.0

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • You can perform automatic Konuşma Tanıma (ASR) streams.
  • You can run the multilingual Metin Okuma (TTS) models.
  • You can train AI models focused on sound and speech.
User reviews
  • • NeutralHacker News

    Whistle: Speech to Text in 16.9 MB

    “I find the quality of transcription quite poor with a high error rate. And I'm using an Devine podcast quality microphone. IMHO the error rate is comparable to Dragon Speech of twenty years ago. It seems to me the speech models don't take into account the context of the words in…”

  • • NeutralHacker News

    Mozilla Common Voice Adds 16 New Languages and 4,600 New Hours of Speech

    “This is silly. Common Voice is not adding NVidia-specific features; what would that even look like for a database? There is no comparison to be made between donating resources to an openly licensed database and encouraging developers to optimize their games for proprietary APIs.…”

Website GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech