It's fast - but for an API, not the fastest speech-to-text. For a long while I hadn't done research and trusted them. Then tried Whisper and Picovoice. On-device latency is nothing comparable with cloud APIs. If latency is important go with Whisper or Picovoice. If customization is also important go with Picovoice.
don't get me wrong it's still faster than amazon, Microsoft or Assemblyai
Deepgram might be a bit more popular than Rhasspy. We know about 27 links to it since March 2021 and only 23 links to Rhasspy. We are tracking product recommendations and mentions on various public social media platforms and blogs. They can help you identify which product is more popular and what people think of it.
Lastly, we will be using Deepgram Audio Diarization APIs to get speaker details from a sample audio clip. - Source: dev.to / 4 months ago
There are other AI-powered APIs out there to consider, too. For example, Deepgram can be used to transcribe audio (better than Whisper, offered by OpenAI), ElevenLabs can be used to generate speech from text (including using custom voices, which OpenAI's TTS can't currently do), etc. Depending on what you're trying to make, a combination of these services may be what you need. In any case, Python is going to be... Source: 5 months ago
This guide delves deep into the world of YouTube video summarization, harnessing the power of cutting-edge technologies including Deepgram for superior audio transcription, Langchain for harvesting the power of the LLM, and Mistral 7B, a state-of-the-art and open-source LLM. - Source: dev.to / 5 months ago
Historically it's been challenging to provide closed captioning for live experiences, be it a live interview, a sports game with commentary, or a livestream. But Deepgram's AI tooling has changed this, allowing users to easily convert realtime streams of audio into accurate transcripts. - Source: dev.to / 6 months ago
To deliver the best possible output, we’ve tested a wide range of AI models and supporting tools. Today, we’re producing industry-leading clinical notes text by combining Deepgram’s highly capable transcription models, ScienceIO’s healthcare-specific AI for processing medical data, and the Microsoft Azure OpenAI GPT-4 large language model. We’ve worked closely with all three teams to bring this new capability to... - Source: dev.to / 7 months ago
Rhasspy seems promising and I started to tinker with it, but didn't get to a functional state before I got distracted by something else. Source: 5 months ago
Alternatively you could try using rhasspy under termux. Source: 11 months ago
Rhasspy might have a lot of what you're looking for: Https://rhasspy.readthedocs.io/en/latest/. Source: almost 1 year ago
There's many voice control options for HA, both private ones like Rhasspy and the corporate spyware ones that only an idiot would use. Source: over 1 year ago
Rhasspy is amazing and more capable than Mycroft (e.g. Satellite support, something that’s mandatory imo), but even more DIY and beginner-unfriendly. That said, the docs are decent, the community is helpful. Source: over 1 year ago
Speechmatics - The most accurate and inclusive speech-to-text API ever released.
Mycroft.AI - Mycroft is the world’s first open source assistant.
AssemblyAI - Speech Recognition for Everyone and Everything.
Google Assistant - Get things done with Google Assistant
Fraim - Fraim is a fully functional transcription service provider that allow the people to download the transcript services in the format that they require and even use the secure Fraim Channel to share the newly and searchable and interactive media with o…
VoiceAttack - VoiceAttack will take commands that you speak into your microphone