# DeepSpeech based automated transcription service

> We have been building a DeepSpeech model with our data for the past year and we have recently hit 95% accuracy on the LibriSpeech dataset. That puts us close to the published results for DeepSpeech 2. However our dataset is conversational audio and we do much better with our own internal dataset co…

Page: https://nowfound.app/launch/deepspeech-based-automated-transcription-service

- Launched: 2018-06-28
- Launch-day votes: 67, 26 comments; #615 of 2,317 launches that month (top 27%)
- Category: [Life & fun](https://nowfound.app/c/life-and-consumer.md)

## In plain words

This automated transcription service uses a DeepSpeech model trained on conversational audio to achieve 95% accuracy on the LibriSpeech dataset. Built over a year of development, it performs better on conversational speech than existing alternatives. The tool is designed for users who need to transcribe audio quickly, though it acknowledges that human transcribers still achieve higher accuracy. The service offers free automated transcripts for a limited time.

## Does a similar job

- [DeepGram](https://nowfound.app/launch/deepgram): Drag and drop speech transcript editor that learns from you (2016-03-17, 819 votes, deepgram.com)
- [Conversational AI 2.0 From ElevenLabs](https://nowfound.app/launch/conversational-ai-2-0-from-elevenlabs): Luke from ElevenLabs here. We just released Scribe Realtime v2, our new real-time Speech to Text model. We rebuilt it from the ground up around a new architecture that uses predictive transcription –… (2025-06-01, 652 votes, free tier, from $6/mo, elevenlabs.io)
- [AssemblyAI](https://nowfound.app/launch/assemblyai-speech-to-text-api): APIs to automatically transcribe and understand audio (2017-08-04, 996 votes, assemblyai.com)
- [Moonshine Open-Weights STT models](https://nowfound.app/launch/moonshine-open-weights-stt-models-higher-accuracy-than-whisp): Moonshine offers open-weights speech-to-text models that achieve lower word-error rates than OpenAI's Whisper Large v3, built by a six-person startup. (2026-02-24, 316 votes, free, github.com)
- [Transcriptal](https://nowfound.app/launch/transcriptal): Free AI powered Youtube transcription platform (2023-12-05, 118 votes, free, pohonemas33.io)
- [Speechtext.ai](https://nowfound.app/launch/speechtext-ai-automated-transcription-service-with-human-acc): AI software for speech to text conversion and audio/video transcription. Get accurate results using domain-specific speech recognition engine! Start for free. (2020-08-28, 12 votes, speechtext.ai)

All alternatives: https://nowfound.app/alternatives/deepspeech-based-automated-transcription-service.md

## For the maker of DeepSpeech based automated transcription service

- Feature it at the top of the NowFound home page for $19 for 30 days, marked sponsored: https://nowfound.app/feature/deepspeech-based-automated-transcription-service
- Free: put the badge on the product's own site and it joins Featured products after the paid spots. HTML for the footer: `<a href="https://nowfound.app/launch/deepspeech-based-automated-transcription-service"><img src="https://nowfound.app/badge/deepspeech-based-automated-transcription-service.svg" alt="DeepSpeech based automated transcription service on NowFound" height="32"></a>`

Source: [Show HN post](https://news.ycombinator.com/item?id=17415900)
