Hacker ApprovedDepartments

Deepgram

Ranked 17 of 25 speech recognition models by recommenders

People recommend Deepgram for accurate speech-to-text, diarization and low latency, with a free tier for personal use. Its text-to-speech is seen as weaker than some rivals.

People recommend Deepgram for accurate speech-to-text, diarization and low latency, with a free tier for personal use. Its text-to-speech is seen as weaker than some rivals.

10 people gave an opinion

recommend it
8
criticize it
2
approval share
80%
Each figure is one person. RecommendsCriticizes

Recommended in 8 of 13 months

  1. November 2025: not recommended
  2. December 2025: recommended
  3. January 2026: recommended
  4. February 2026: not recommended
  5. March 2026: not recommended
  6. April 2026: recommended
  7. May 2026: recommended
  8. June 2026: recommended
  9. July 2026: not recommended
  10. August 2026: recommended
  11. September 2026: recommended
  12. October 2026: recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 8 people recommend itNeeds 10 or more, not met.
  • 4 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 8 of 13 monthsNeeds 4 or more, met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Strong speech-to-text and diarization

    “Deepgram is really good for diorization. And speech to text, but they're not as good as the others for text to speech.”

    Comment from 28 Jan 2026 in “Show HN: CLI for text-to-speech using OpenAI/Deepgram/Elevenlabs”

    “deepgram seems really good (esp Enhanced and Nova 3 models).”

    Comment from 1 Apr 2026 in “Cohere Transcribe: Speech Recognition”

    “have models that are genuinely good”

    Comment from 14 Jun 2026 in “Ask HN: What are you working on? (June 2026)”
  • Top choice among speech APIs

    “I've found Deepgram to be the most pragmatic choice lately”

    Comment from 26 Jan 2026 in “Show HN: CLI for text-to-speech using OpenAI/Deepgram/Elevenlabs”

    “others do it very well, like Soniox and Deepgram”

    Comment from 28 Aug 2026 in “Gemini-3.5-Transcribe”

    “Deepgram does that wonderfully.”

    Comment from 5 May 2026 in “How OpenAI delivers low-latency voice AI at scale”
  • Lower latency than alternatives

    “We moved a similar stack to Deepgram recently and the latency is significantly better”

    Comment from 27 Jan 2026 in “We Built Our IVR Scraper (and What Broke Along the Way)”

    “hooked up for a better voice to text experience”

    Comment from 5 Sep 2026 in “LLMs as a Cognitive Virus”

What people warn about

Each mark is one comment

  • Weaker than rivals at text-to-speech

    “Deepgram is really good for diorization. And speech to text, but they're not as good as the others for text to speech.”

    Comment from 28 Jan 2026 in “Show HN: CLI for text-to-speech using OpenAI/Deepgram/Elevenlabs”

    “It really does do way better than Deepgram and others.”

    Comment from 3 Mar 2026 in “Show HN: I built a sub-500ms latency voice agent from scratch”

Other speech recognition models people recommend

The four most recommended other speech recognition models, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

Deepgram compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
OpenAI Whisper1645376%12—Approved
NVIDIA Parakeet1442784%12—Approved
Mistral Voxtral692772%8—Approved
Moonshine open-weights STT models371374%7—Approved
DeepgramThis page8280%8——
See all 25 speech recognition models, ranked

What people said

11 of the 12 comments that mention it, newest first. Each links to the original comment.

“This is the main reason I lean on Deepgram over local services.”

RecommendsComment from 8 Oct 2026 in “Whistle: Speech to Text in 16.9 MB”

“hooked up for a better voice to text experience”

RecommendsComment from 5 Sep 2026 in “LLMs as a Cognitive Virus”

“others do it very well, like Soniox and Deepgram”

RecommendsComment from 28 Aug 2026 in “Gemini-3.5-Transcribe”

“have models that are genuinely good”

RecommendsComment from 14 Jun 2026 in “Ask HN: What are you working on? (June 2026)”

“Deepgram does that wonderfully.”

RecommendsComment from 5 May 2026 in “How OpenAI delivers low-latency voice AI at scale”

“deepgram seems really good (esp Enhanced and Nova 3 models).”

RecommendsComment from 1 Apr 2026 in “Cohere Transcribe: Speech Recognition”

“It really does do way better than Deepgram and others.”

CriticizesComment from 3 Mar 2026 in “Show HN: I built a sub-500ms latency voice agent from scratch”

“Deepgram is really good for diorization. And speech to text, but they're not as good as the others for text to speech.”

MixedComment from 28 Jan 2026 in “Show HN: CLI for text-to-speech using OpenAI/Deepgram/Elevenlabs”

“We moved a similar stack to Deepgram recently and the latency is significantly better”

RecommendsComment from 27 Jan 2026 in “We Built Our IVR Scraper (and What Broke Along the Way)”

“I've found Deepgram to be the most pragmatic choice lately”

RecommendsComment from 26 Jan 2026 in “Show HN: CLI for text-to-speech using OpenAI/Deepgram/Elevenlabs”

“their free tier is basically unlimited for personal use, so $0 forever”

RecommendsComment from 1 Dec 2025 in “Wispr Flow raised $81M for this. I open-sourced it: jarvis.ceo (free forever)”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.