--- title: Filler Words in Speech-to-Text: Verbatim vs Clean Output description: Deepgram's filler_words parameter governs seven tokens, but the default (false) only strips two hesitation markers, uh and um. The other five tokens (mhmm,... canonical: https://daily.dev/posts/filler-words-in-speech-to-text-verbatim-vs-clean-output-8t4uotbei twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Filler Words in Speech-to-Text: Verbatim vs Clean Output | daily.dev og:description: Deepgram's filler_words parameter governs seven tokens, but the default (false) only strips two hesitation markers, uh and um. The other five tokens (mhmm,... og:url: https://daily.dev/posts/filler-words-in-speech-to-text-verbatim-vs-clean-output-8t4uotbei og:image: https://api.daily.dev/og/posts/8t4UOTbEi.png og:image:alt: Filler Words in Speech-to-Text: Verbatim vs Clean Output og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Filler Words in Speech-to-Text: Verbatim vs Clean Output **[Deepgram](https://daily.dev/sources/deepgram)** · 12 min read · 0 upvotes · 0 comments ## Summary Deepgram's filler_words parameter governs seven tokens, but the default (false) only strips two hesitation markers, uh and um. The other five tokens (mhmm, mm-mm, uh-uh, uh-huh, nuh-uh) are backchannel agreement/disagreement signals, and Deepgram's own docs table shows uh-huh surviving the default while leaving the other four unclassified. This matters for court records, clinical notes, and LLM pipelines, since a clean-looking transcript can still hide a spoken yes or no. The piece walks through legal and clinical transcription standards, model support inconsistencies across Deepgram's docs (Nova vs Nova-3 vs Flux), English-only language coverage, and gives a decision table for when to enable verbatim mode versus the clean default. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What does Deepgram's filler_words parameter default to and what does it actually remove? The filler_words parameter defaults to false on Deepgram's Nova-family models, and at that default only two tokens are stripped from the transcript: uh and um. Deepgram detects seven tokens total (uh, um, mhmm, mm-mm, uh-uh, uh-huh, nuh-uh), but the docs only confirm uh and um as removed; uh-huh is shown surviving the default in Deepgram's own results table, while mhmm, mm-mm, uh-uh, and nuh-uh remain unclassified at default. _Anyone tuning transcript pipelines for legal or clinical accuracy can track API parameter quirks like this via daily.dev._ ### Are uh-huh and uh-uh hesitation markers or answers in speech transcription? They are backchannel answers, not hesitation markers. Five of Deepgram's seven documented filler tokens (mhmm, mm-mm, uh-uh, uh-huh, nuh-uh) are listener agreement or disagreement signals rather than speaker stalling sounds; only uh and um mark hesitation. uh-huh typically reads as yes and uh-uh as no, differing by a single letter, so stripping them can erase a spoken answer. _Teams building transcript-to-LLM pipelines can weigh tradeoffs like this on daily.dev before picking a setting._ ### Which Deepgram models support the filler_words parameter? Deepgram's documentation pages disagree with each other on this. The feature page limits filler word support to Nova, Nova-2, and Nova-3 general models, but the Flux and Nova-3 comparison table marks Nova-3 as unsupported while listing Flux as supported, and the models overview page separately recommends Nova-2 for filler word identification. The feature is English-only across all available regions. _Developers comparing speech-to-text model coverage can cross-check conflicting vendor docs via daily.dev._ ## Similar posts on daily.dev - [Backchannels vs Interruptions in Voice Agents](https://daily.dev/posts/backchannels-vs-interruptions-in-voice-agents-w7kbvmglt) · Deepgram · 0 upvotes · 0 comments - [Conversation Context for Voice Agents: Accuracy Guide](https://daily.dev/posts/conversation-context-for-voice-agents-accuracy-guide-nvai7bs4k) · Deepgram · 0 upvotes · 0 comments - [The key to conversational speech recognition](https://daily.dev/posts/the-key-to-conversational-speech-recognition-zhup6uyph) · Data Science Central · 0 upvotes · 0 comments --- Tags: [#architecture](https://daily.dev/tags/architecture), [#nlp](https://daily.dev/tags/nlp), [#speech-recognition](https://daily.dev/tags/speech-recognition), [#deepgram](https://daily.dev/tags/deepgram) [View this post on daily.dev](https://daily.dev/posts/filler-words-in-speech-to-text-verbatim-vs-clean-output-8t4uotbei) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Filler Words in Speech-to-Text: Verbatim vs Clean Output","url":"https://daily.dev/posts/filler-words-in-speech-to-text-verbatim-vs-clean-output-8t4uotbei","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/filler-words-in-speech-to-text-verbatim-vs-clean-output-8t4uotbei"},"datePublished":"2026-09-03T19:03:28.273Z","dateModified":"2026-09-03T20:43:47.998Z","description":"Deepgram's filler_words parameter governs seven tokens, but the default (false) only strips two hesitation markers, uh and um. The other five tokens (mhmm,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b96f824263b5ddf49e81a95ab90c3dba?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/b96f824263b5ddf49e81a95ab90c3dba?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Deepgram","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Deepgram","logo":"https://media.daily.dev/image/upload/s--e63hOwKU--/f_auto/v1716188454/logos/deepgram","url":"https://daily.dev/sources/deepgram"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/filler-words-in-speech-to-text-verbatim-vs-clean-output-8t4uotbei","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"architecture,nlp,speech-recognition,deepgram","timeRequired":"PT12M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Deepgram","item":"https://daily.dev/sources/deepgram"},{"@type":"ListItem","position":3,"name":"Filler Words in Speech-to-Text: Verbatim vs Clean Output"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/filler-words-in-speech-to-text-verbatim-vs-clean-output-8t4uotbei#faq","mainEntity":[{"@type":"Question","name":"What does Deepgram's filler_words parameter default to and what does it actually remove?","acceptedAnswer":{"@type":"Answer","text":"The filler_words parameter defaults to false on Deepgram's Nova-family models, and at that default only two tokens are stripped from the transcript: uh and um. Deepgram detects seven tokens total (uh, um, mhmm, mm-mm, uh-uh, uh-huh, nuh-uh), but the docs only confirm uh and um as removed; uh-huh is shown surviving the default in Deepgram's own results table, while mhmm, mm-mm, uh-uh, and nuh-uh remain unclassified at default. Anyone tuning transcript pipelines for legal or clinical accuracy can track API parameter quirks like this via daily.dev."}},{"@type":"Question","name":"Are uh-huh and uh-uh hesitation markers or answers in speech transcription?","acceptedAnswer":{"@type":"Answer","text":"They are backchannel answers, not hesitation markers. Five of Deepgram's seven documented filler tokens (mhmm, mm-mm, uh-uh, uh-huh, nuh-uh) are listener agreement or disagreement signals rather than speaker stalling sounds; only uh and um mark hesitation. uh-huh typically reads as yes and uh-uh as no, differing by a single letter, so stripping them can erase a spoken answer. Teams building transcript-to-LLM pipelines can weigh tradeoffs like this on daily.dev before picking a setting."}},{"@type":"Question","name":"Which Deepgram models support the filler_words parameter?","acceptedAnswer":{"@type":"Answer","text":"Deepgram's documentation pages disagree with each other on this. The feature page limits filler word support to Nova, Nova-2, and Nova-3 general models, but the Flux and Nova-3 comparison table marks Nova-3 as unsupported while listing Flux as supported, and the models overview page separately recommends Nova-2 for filler word identification. The feature is English-only across all available regions. Developers comparing speech-to-text model coverage can cross-check conflicting vendor docs via daily.dev."}}]} ```