{"slug": "elevenlabs", "name": "ElevenLabs", "category": "ai", "category_name": "AI models and assistants", "description": "AI voice platform for text-to-speech, voice cloning, transcription and conversational voice agents.", "recommenders": 6, "commenters": 18, "warners": 1, "score": 7.493, "rising": 2.02, "first": "2025-11-06", "latest": "2026-10-31", "why": "Used mostly for natural-sounding voiceovers and narration, plus speech-to-text and phone voice agents built on its API.", "why_is_quote": false, "has_verdict": true, "sentiment": {"recommend": 6, "neutral": 10, "compare": 1, "warn": 1}, "spark": [0, 0, 2, 0, 0, 1, 0, 0, 0, 1, 0, 2], "listed": true, "loved": ["Voiceovers", "Voice quality"], "caveat": "Real-time limits", "short_quote": "If you want to get real good quality TTS, you should check out elevenlabs.io", "icon": true, "domain": "elevenlabs.io", "github_repo": null, "official_url": "https://elevenlabs.io", "pricing": "freemium", "aliases": ["ElevenLabs"], "verdict": [{"text": "Used mostly for natural-sounding voiceovers and narration", "cites": [{"id": 763480481, "item_id": 47717530, "url": "https://news.ycombinator.com/item?id=47717530", "by": "Areena_28", "date": "2026-04-10", "stance": "recommend", "quote": "Eleven Labs made voiceover work that used to cost thousands into a $5 task", "excerpt": "The disruption is 101% happening but it's mostly invisible from the outside. iI think its not new apps replacing old ones rather the same apps doing things that used to require 3x the headcount. That said there are a few genuine examples Cursor basically replaced how a lot of developers write code, Eleven Labs made voiceover work that used to cost thousands into a $5 task, and Gamma turned presentations from a half-d", "context": "", "use_case": "voiceover", "switched_from": "", "story": "Ask HN: Where are all the disruptive software that AI promised?"}, {"id": 798105826, "item_id": 49881614, "url": "https://news.ycombinator.com/item?id=49881614", "by": "scosman", "date": "2026-09-28", "stance": "neutral", "quote": "can generate voiceover with elevenlabs", "excerpt": "These AI explainers are taking over. I tried getting this working back in May. The models were okay but not quite there and it was a ton of effort. Opus 5.5 seems like the tipping point. I made an OSS framework for these for when you want to go beyond one-shoting it: https://github.com/scosman/videowright - Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and ", "context": "", "use_case": "voiceover generation", "switched_from": "", "story": "Show HN: HN.watch \u2013 Videos of all Hacker News posts"}, {"id": 804988913, "item_id": 50311807, "url": "https://news.ycombinator.com/item?id=50311807", "by": "Jash271", "date": "2026-10-31", "stance": "neutral", "quote": "ElevenLabs for the voice", "excerpt": "Agents interacting with each other made for great content, so we created a series out of it: https://www.youtube.com/watch?v=dxXvgM75yis PS: I'm not a video editor. I used Claude to generate the videos, ElevenLabs for the voice, and GPT for the images of the characters", "context": "not a video editor", "use_case": "voice generation", "switched_from": "", "story": "Where AI agents' social boundaries break: 5 LLMs try to form a government"}, {"id": 744828896, "item_id": 46551806, "url": "https://news.ycombinator.com/item?id=46551806", "by": "Mashimo", "date": "2026-01-09", "stance": "recommend", "quote": "If you want to get real good quality TTS, you should check out elevenlabs.io", "excerpt": "Here is an overview: https://www.inferless.com/learn/comparing-different-text-to-speech---tts--models-part-2 Also keep in mind the processing time. The ^ article above used a NVIDIA L4 with 24-GB VRAM. Sopro claims 7.5 second processing time on CPU for 30 seconds of audio! If you want to get real good quality TTS, you should check out elevenlabs.io Different tools for different goals.", "context": "", "use_case": "high-quality text-to-speech", "switched_from": "", "story": "Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU"}, {"id": 805034800, "item_id": 50314675, "url": "https://news.ycombinator.com/item?id=50314675", "by": "cheesedoodle", "date": "2026-10-31", "stance": "recommend", "quote": "I selected Roger - Laid back Casual and Resonant, and it came out quite good!", "excerpt": "I used elevenlabs to generate speech-to-text for this article. I selected Roger - Laid back Casual and Resonant, and it came out quite good!", "context": "", "use_case": "narrating an article", "switched_from": "", "story": "LLM Voice"}]}, {"text": ", plus speech-to-text and phone voice agents built on its API.", "cites": [{"id": 747830992, "item_id": 46739437, "url": "https://news.ycombinator.com/item?id=46739437", "by": "Johnny_Bonk", "date": "2026-01-23", "stance": "recommend", "quote": "use eleven labs api which is pretty generous", "excerpt": "Nice I'll try it, as of now for my personal stt workflow I use eleven labs api which is pretty generous but curious to play around with other options", "context": "", "use_case": "speech-to-text workflow", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 755636947, "item_id": 47227309, "url": "https://news.ycombinator.com/item?id=47227309", "by": "suganesh95", "date": "2026-03-02", "stance": "neutral", "quote": "elevenlabs for STT", "excerpt": "I built something very similar and comparble to this with wakeword detection on my raaberry pi. Groq 8b instant is the fastest llm from my test. I used smallest ai for tts as it has the smallest TTFT My rasberry pi stack: porcupine for wakeword detection + elevenlabs for STT + groq scout as it supports home automation better + smallest.ai for 70ms ttfb Call stack: twilio + groq whisper for STT + groq 8b instant + sma", "context": "", "use_case": "speech-to-text", "switched_from": "", "story": "Show HN: I built a sub-500ms latency voice agent from scratch"}, {"id": 790486112, "item_id": 49405382, "url": "https://news.ycombinator.com/item?id=49405382", "by": "dannyw", "date": "2026-08-23", "stance": "recommend", "quote": "11labs does _way_ more than basic TTS.", "excerpt": "11labs does _way_ more than basic TTS. The options, customizability, quality of voice cloning (for editing your own voices), etc is far more than what you see on the surface. Check out their docs for a glimpse: https://elevenlabs.io/docs/api-reference/introduction If you wanna hook up a voice agent to Twilio for support for example, 11labs is probably one of the quickest and least painful ways to integrate while stil", "context": "", "use_case": "voice agents, TTS, voice cloning", "switched_from": "", "story": "ElevenLabs, TwelveLabs, ThirteenLabs"}, {"id": 792964561, "item_id": 49560285, "url": "https://news.ycombinator.com/item?id=49560285", "by": "MitziMoto", "date": "2026-09-04", "stance": "neutral", "quote": "On the ElevenLabs platform, you provide them a system prompt", "excerpt": "We use a Twilio integration to make it work over a real phone line, but it could just as well be an app or websocket connection in a browser. Voice transport medium aside, the actual use case is not quite what you described. Companies like Eleven Labs and Vapi provide a full end to end voice agent platform. They handle the STT -> LLM -> TTS pipeline and infrastructure for voice agents. Think of a customer talking to ", "context": "", "use_case": "voice agent platform", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}]}, {"text": " Complaints are rare: one commenter found it not live enough for conversational practice", "cites": [{"id": 794495377, "item_id": 49655961, "url": "https://news.ycombinator.com/item?id=49655961", "by": "adityashankar", "date": "2026-09-11", "stance": "warn", "quote": "I tried it with elevenlabs before but it wasn't live enough and the models were not intelligent enough.", "excerpt": "Oh yeah, I built so much stuff to learn German, for example [1] to give me random German texts, force me to read it, and answer it, I created [2] to automatically make flashcards for me and then use with with a flashcards app I regularly use and [3] to help me memorise German cases and word-genders. I love it! I did think of implementing this conversationally, but tbh it has always been too expensive thus far, I gott", "context": "learning German", "use_case": "conversational language practice", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}]}, {"text": ", and another says Kokoro comes close except against ElevenLabs' larger models and professional voices.", "cites": [{"id": 781203649, "item_id": 48825228, "url": "https://news.ycombinator.com/item?id=48825228", "by": "rnxrx", "date": "2026-07-07", "stance": "compare", "quote": "Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well", "excerpt": "Another endorsement - I used Kokoro pretty extensively with an app I was developing over the last year and it's been excellent, both on- and off- GPU. Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well until you get to their larger models with their professional voices. I do wish there were better support for SSML, as well as deeper documentation of how to influence inf", "context": "", "use_case": "TTS", "switched_from": "", "story": "Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro"}]}], "praise": [{"label": "Voiceovers", "summary": "Commenters use it to voice videos, ads and explainers, and one says it turned costly voiceover work into a $5 task.", "quotes": [{"id": 763480481, "item_id": 47717530, "url": "https://news.ycombinator.com/item?id=47717530", "by": "Areena_28", "date": "2026-04-10", "stance": "recommend", "quote": "Eleven Labs made voiceover work that used to cost thousands into a $5 task", "excerpt": "The disruption is 101% happening but it's mostly invisible from the outside. iI think its not new apps replacing old ones rather the same apps doing things that used to require 3x the headcount. That said there are a few genuine examples Cursor basically replaced how a lot of developers write code, Eleven Labs made voiceover work that used to cost thousands into a $5 task, and Gamma turned presentations from a half-d", "context": "", "use_case": "voiceover", "switched_from": "", "story": "Ask HN: Where are all the disruptive software that AI promised?"}, {"id": 798105826, "item_id": 49881614, "url": "https://news.ycombinator.com/item?id=49881614", "by": "scosman", "date": "2026-09-28", "stance": "neutral", "quote": "can generate voiceover with elevenlabs", "excerpt": "These AI explainers are taking over. I tried getting this working back in May. The models were okay but not quite there and it was a ton of effort. Opus 5.5 seems like the tipping point. I made an OSS framework for these for when you want to go beyond one-shoting it: https://github.com/scosman/videowright - Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and ", "context": "", "use_case": "voiceover generation", "switched_from": "", "story": "Show HN: HN.watch \u2013 Videos of all Hacker News posts"}, {"id": 803232497, "item_id": 50202031, "url": "https://news.ycombinator.com/item?id=50202031", "by": "adeiji1", "date": "2026-10-22", "stance": "neutral", "quote": "We use ElevenLabs for the music and the VoiceOver", "excerpt": "I\u2019ve shipped several SaaS products, and the largest problem has always been the same\u2026marketing. This pain point has become even worse due to the ease of building products with AI. But now, because of AI, we can simplify the marketing process and include it in the build pipeline. I call this process Continuous Advertising/Continuous Marketing or CA/CM. Much like CI/CD, MarketMee watches for GitHub pushes, scans your c", "context": "", "use_case": "music and voiceover", "switched_from": "", "story": "Show HN: MarketMee - Every GitHub push becomes a narrated product video"}]}, {"label": "Voice quality", "summary": "Recommended when you want really good quality TTS, with voices that come out well.", "quotes": [{"id": 744828896, "item_id": 46551806, "url": "https://news.ycombinator.com/item?id=46551806", "by": "Mashimo", "date": "2026-01-09", "stance": "recommend", "quote": "If you want to get real good quality TTS, you should check out elevenlabs.io", "excerpt": "Here is an overview: https://www.inferless.com/learn/comparing-different-text-to-speech---tts--models-part-2 Also keep in mind the processing time. The ^ article above used a NVIDIA L4 with 24-GB VRAM. Sopro claims 7.5 second processing time on CPU for 30 seconds of audio! If you want to get real good quality TTS, you should check out elevenlabs.io Different tools for different goals.", "context": "", "use_case": "high-quality text-to-speech", "switched_from": "", "story": "Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU"}, {"id": 805034800, "item_id": 50314675, "url": "https://news.ycombinator.com/item?id=50314675", "by": "cheesedoodle", "date": "2026-10-31", "stance": "recommend", "quote": "I selected Roger - Laid back Casual and Resonant, and it came out quite good!", "excerpt": "I used elevenlabs to generate speech-to-text for this article. I selected Roger - Laid back Casual and Resonant, and it came out quite good!", "context": "", "use_case": "narrating an article", "switched_from": "", "story": "LLM Voice"}, {"id": 781203649, "item_id": 48825228, "url": "https://news.ycombinator.com/item?id=48825228", "by": "rnxrx", "date": "2026-07-07", "stance": "compare", "quote": "Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well", "excerpt": "Another endorsement - I used Kokoro pretty extensively with an app I was developing over the last year and it's been excellent, both on- and off- GPU. Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well until you get to their larger models with their professional voices. I do wish there were better support for SSML, as well as deeper documentation of how to influence inf", "context": "", "use_case": "TTS", "switched_from": "", "story": "Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro"}]}, {"label": "Voice agents", "summary": "Offers an end-to-end voice agent platform that one commenter calls one of the quickest ways to hook an agent up to Twilio.", "quotes": [{"id": 790486112, "item_id": 49405382, "url": "https://news.ycombinator.com/item?id=49405382", "by": "dannyw", "date": "2026-08-23", "stance": "recommend", "quote": "11labs does _way_ more than basic TTS.", "excerpt": "11labs does _way_ more than basic TTS. The options, customizability, quality of voice cloning (for editing your own voices), etc is far more than what you see on the surface. Check out their docs for a glimpse: https://elevenlabs.io/docs/api-reference/introduction If you wanna hook up a voice agent to Twilio for support for example, 11labs is probably one of the quickest and least painful ways to integrate while stil", "context": "", "use_case": "voice agents, TTS, voice cloning", "switched_from": "", "story": "ElevenLabs, TwelveLabs, ThirteenLabs"}, {"id": 792964561, "item_id": 49560285, "url": "https://news.ycombinator.com/item?id=49560285", "by": "MitziMoto", "date": "2026-09-04", "stance": "neutral", "quote": "On the ElevenLabs platform, you provide them a system prompt", "excerpt": "We use a Twilio integration to make it work over a real phone line, but it could just as well be an app or websocket connection in a browser. Voice transport medium aside, the actual use case is not quite what you described. Companies like Eleven Labs and Vapi provide a full end to end voice agent platform. They handle the STT -> LLM -> TTS pipeline and infrastructure for voice agents. Think of a customer talking to ", "context": "", "use_case": "voice agent platform", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}, {"id": 792961904, "item_id": 49560119, "url": "https://news.ycombinator.com/item?id=49560119", "by": "MitziMoto", "date": "2026-09-04", "stance": "neutral", "quote": "point any voice agent platform we choose -- eleven labs, vapi, pipecat, whatever", "excerpt": "We use MCP in production for our customer facing voice agents. Our custom MCP server defines tools and resources that the voice agents need access to to interact with our customers. (E.g. scheduling appointments, checking order status, etc). Now we can point any voice agent platform we choose -- eleven labs, vapi, pipecat, whatever -- at our custom MCP server and it instantly has an understanding of the tools availab", "context": "", "use_case": "customer-facing voice agents", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}]}, {"label": "Speech-to-text", "summary": "Used for transcription and STT workflows, with one commenter calling the API pretty generous.", "quotes": [{"id": 747830992, "item_id": 46739437, "url": "https://news.ycombinator.com/item?id=46739437", "by": "Johnny_Bonk", "date": "2026-01-23", "stance": "recommend", "quote": "use eleven labs api which is pretty generous", "excerpt": "Nice I'll try it, as of now for my personal stt workflow I use eleven labs api which is pretty generous but curious to play around with other options", "context": "", "use_case": "speech-to-text workflow", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 755636947, "item_id": 47227309, "url": "https://news.ycombinator.com/item?id=47227309", "by": "suganesh95", "date": "2026-03-02", "stance": "neutral", "quote": "elevenlabs for STT", "excerpt": "I built something very similar and comparble to this with wakeword detection on my raaberry pi. Groq 8b instant is the fastest llm from my test. I used smallest ai for tts as it has the smallest TTFT My rasberry pi stack: porcupine for wakeword detection + elevenlabs for STT + groq scout as it supports home automation better + smallest.ai for 70ms ttfb Call stack: twilio + groq whisper for STT + groq 8b instant + sma", "context": "", "use_case": "speech-to-text", "switched_from": "", "story": "Show HN: I built a sub-500ms latency voice agent from scratch"}, {"id": 778736032, "item_id": 48671002, "url": "https://news.ycombinator.com/item?id=48671002", "by": "Protostome", "date": "2026-06-25", "stance": "neutral", "quote": "I ran it through ElevenLabs transcription and GPT5.5 based translation of the transcript", "excerpt": "Did you encounter any mistranslation here specifically? it's pretty easy to translate the video with Gemini or a different AI tool. I did it - I ran it through ElevenLabs transcription and GPT5.5 based translation of the transcript, this is what I got: 00:00:16,479 --> 00:00:34,520 [Speaker 0] And I pray in every prayer \u2014 every prayer, every prayer \u2014 that I, your father, your sisters, girls and boys, all of you, will", "context": "", "use_case": "audio transcription", "switched_from": "", "story": "Israel targeted Gaza children resulting in genocide, UN inquiry says"}]}, {"label": "Audiobooks", "summary": "Commenters generate or listen to audiobooks with it.", "quotes": [{"id": 787698993, "item_id": 49231187, "url": "https://news.ycombinator.com/item?id=49231187", "by": "thepoet", "date": "2026-08-09", "stance": "neutral", "quote": "generate audiobooks on topics I want to understand with ElevenLabs, Exa and OpenAI", "excerpt": "I have a Kobo that was kept unused in a similar state for a few years until I decide to build an SDK platform to develop and deploy apps on it. My Kobo does not support apps on its Linux platform. I have been using it to read HN, as an RSS reader over my news and blog sources, generate audiobooks on topics I want to understand with ElevenLabs, Exa and OpenAI and listen via connecting its bluetooth to my speakers and ", "context": "", "use_case": "generating audiobooks", "switched_from": "", "story": "Reviving a four year old reMarkable 2"}, {"id": 786551443, "item_id": 49159465, "url": "https://news.ycombinator.com/item?id=49159465", "by": "thepoet", "date": "2026-08-03", "stance": "neutral", "quote": "an audiobook generator using deep research and ElevenLabs API", "excerpt": "A bit idealistic for the crowd here but has some good points. The other day I wanted to build personal apps for my Kobo device. It has a single ~800Mhz core and 512 MB of RAM, probably eight times less than a rasbperry pi, but runs a Linux. I wanted to break free from watching my laptop screen for long Claude sessions partially due to degrading eyesight and have a sidekick for approvals streamed to the Kobo. Apart fr", "context": "", "use_case": "audiobook generation", "switched_from": "", "story": "Devtools must be open source"}, {"id": 785341888, "item_id": 49083868, "url": "https://news.ycombinator.com/item?id=49083868", "by": "wrsh07", "date": "2026-07-28", "stance": "neutral", "quote": "I listened to some books from standard ebooks using eleven labs", "excerpt": "This is great! I would love an explicit \"set bookmark to here\" button if I scroll up from the high watermark I discovered the reset, but it took a minute and I expect given the way I read being able to explicitly walk the high watermark back a bit would be nice (maybe that's doable if you select text? I didn't try!) The format is nice, I love standard ebooks I opened Moby Dick but didn't see how to listen to it on my", "context": "", "use_case": "text-to-speech audiobooks", "switched_from": "", "story": "Show HN: tale.fyi, we deserve a home for fiction"}]}, {"label": "Voice cloning", "summary": "Voice cloning quality and customizability go well beyond basic TTS, and one commenter cloned a TV character's voice.", "quotes": [{"id": 790486112, "item_id": 49405382, "url": "https://news.ycombinator.com/item?id=49405382", "by": "dannyw", "date": "2026-08-23", "stance": "recommend", "quote": "11labs does _way_ more than basic TTS.", "excerpt": "11labs does _way_ more than basic TTS. The options, customizability, quality of voice cloning (for editing your own voices), etc is far more than what you see on the surface. Check out their docs for a glimpse: https://elevenlabs.io/docs/api-reference/introduction If you wanna hook up a voice agent to Twilio for support for example, 11labs is probably one of the quickest and least painful ways to integrate while stil", "context": "", "use_case": "voice agents, TTS, voice cloning", "switched_from": "", "story": "ElevenLabs, TwelveLabs, ThirteenLabs"}, {"id": 733492273, "item_id": 45843267, "url": "https://news.ycombinator.com/item?id=45843267", "by": "tptacek", "date": "2025-11-06", "stance": "neutral", "quote": "synthesized with ElevenLabs", "excerpt": "I recently bought a mint-condition Alf phone, in the shape of Gordon Shumway of TV's \"Alf\", out of the back of an old auto shop in the south suburbs of Chicago, and naturally did the most obvious thing, which was to make a Gordon Shumway phone that has conversations in the voice of Gordon Shumway (sampled from Youtube and synthesized with ElevenLabs). I use https://github.com/etalab-ia/faster-whisper-server (I think?", "context": "", "use_case": "voice synthesis", "switched_from": "", "story": "You should write an agent"}]}], "caveats": [{"label": "Real-time limits", "summary": "One user found it not live enough, and its models not intelligent enough, for conversational German practice.", "quotes": [{"id": 794495377, "item_id": 49655961, "url": "https://news.ycombinator.com/item?id=49655961", "by": "adityashankar", "date": "2026-09-11", "stance": "warn", "quote": "I tried it with elevenlabs before but it wasn't live enough and the models were not intelligent enough.", "excerpt": "Oh yeah, I built so much stuff to learn German, for example [1] to give me random German texts, force me to read it, and answer it, I created [2] to automatically make flashcards for me and then use with with a flashcards app I regularly use and [3] to help me memorise German cases and word-genders. I love it! I did think of implementing this conversationally, but tbh it has always been too expensive thus far, I gott", "context": "learning German", "use_case": "conversational language practice", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}]}, {"label": "Close alternatives", "summary": "A long-time subscriber says Kokoro keeps up in quality until you reach ElevenLabs' larger models and professional voices.", "quotes": [{"id": 781203649, "item_id": 48825228, "url": "https://news.ycombinator.com/item?id=48825228", "by": "rnxrx", "date": "2026-07-07", "stance": "compare", "quote": "Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well", "excerpt": "Another endorsement - I used Kokoro pretty extensively with an app I was developing over the last year and it's been excellent, both on- and off- GPU. Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well until you get to their larger models with their professional voices. I do wish there were better support for SSML, as well as deeper documentation of how to influence inf", "context": "", "use_case": "TTS", "switched_from": "", "story": "Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro"}]}], "who": [{"by": "Jash271", "context": "not a video editor", "url": "https://news.ycombinator.com/item?id=50311807", "date": "2026-10-31"}], "tags": ["for video voiceovers", "for voice agents", "for transcription", "for audiobook generation", "API-first"], "use_cases": ["voice generation", "voiceover generation", "voice synthesis", "narrating an article", "music and voiceover", "voice cloning and tts"], "compared": [{"slug": "claude", "name": "Claude", "co": 3, "switched_from": 0, "switched_to": 0}, {"slug": "gpt", "name": "GPT", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "ffmpeg", "name": "ffmpeg", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "codex", "name": "Codex", "co": 2, "switched_from": 0, "switched_to": 0}, {"slug": "pocket-tts", "name": "Pocket-TTS", "co": 2, "switched_from": 0, "switched_to": 0}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49548600", "title": "Ask HN: Who is using MCP in production?", "mentions": 2}, {"url": "https://news.ycombinator.com/item?id=50290177", "title": "LLM Voice", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50311801", "title": "Where AI agents' social boundaries break: 5 LLMs try to form a government", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50297636", "title": "Where AI agents' social boundaries break: 5 LLMs try to form a government", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50201777", "title": "Show HN: MarketMee - Every GitHub push becomes a narrated product video", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=50181563", "title": "Gemini vs. ElevenLabs Voice Cloning and TTS", "mentions": 1}], "sentiment_by_month": {"2025-11": {"neutral": 1}, "2025-12": {}, "2026-01": {"recommend": 2}, "2026-02": {}, "2026-03": {"neutral": 2}, "2026-04": {"recommend": 1}, "2026-05": {}, "2026-06": {"neutral": 1}, "2026-07": {"compare": 1, "neutral": 1}, "2026-08": {"neutral": 1, "recommend": 1}, "2026-09": {"neutral": 2, "warn": 1}, "2026-10": {"recommend": 2, "neutral": 2}}, "quotes": [{"id": 805034800, "item_id": 50314675, "url": "https://news.ycombinator.com/item?id=50314675", "by": "cheesedoodle", "date": "2026-10-31", "stance": "recommend", "quote": "I selected Roger - Laid back Casual and Resonant, and it came out quite good!", "excerpt": "I used elevenlabs to generate speech-to-text for this article. I selected Roger - Laid back Casual and Resonant, and it came out quite good!", "context": "", "use_case": "narrating an article", "switched_from": "", "story": "LLM Voice"}, {"id": 804988913, "item_id": 50311807, "url": "https://news.ycombinator.com/item?id=50311807", "by": "Jash271", "date": "2026-10-31", "stance": "neutral", "quote": "ElevenLabs for the voice", "excerpt": "Agents interacting with each other made for great content, so we created a series out of it: https://www.youtube.com/watch?v=dxXvgM75yis PS: I'm not a video editor. I used Claude to generate the videos, ElevenLabs for the voice, and GPT for the images of the characters", "context": "not a video editor", "use_case": "voice generation", "switched_from": "", "story": "Where AI agents' social boundaries break: 5 LLMs try to form a government"}, {"id": 804762401, "item_id": 50297650, "url": "https://news.ycombinator.com/item?id=50297650", "by": "Jash271", "date": "2026-10-29", "stance": "neutral", "quote": "ElevenLabs for the voice", "excerpt": "Agents interacting with each other made for great content, so we created a series out of it: https://www.youtube.com/watch?v=dxXvgM75yis PS: I'm not a video editor. I used Claude to generate the videos, ElevenLabs for the voice, and GPT for the images of the characters.", "context": "", "use_case": "voice generation", "switched_from": "", "story": "Where AI agents' social boundaries break: 5 LLMs try to form a government"}, {"id": 803232497, "item_id": 50202031, "url": "https://news.ycombinator.com/item?id=50202031", "by": "adeiji1", "date": "2026-10-22", "stance": "neutral", "quote": "We use ElevenLabs for the music and the VoiceOver", "excerpt": "I\u2019ve shipped several SaaS products, and the largest problem has always been the same\u2026marketing. This pain point has become even worse due to the ease of building products with AI. But now, because of AI, we can simplify the marketing process and include it in the build pipeline. I call this process Continuous Advertising/Continuous Marketing or CA/CM. Much like CI/CD, MarketMee watches for GitHub pushes, scans your c", "context": "", "use_case": "music and voiceover", "switched_from": "", "story": "Show HN: MarketMee - Every GitHub push becomes a narrated product video"}, {"id": 802906672, "item_id": 50181667, "url": "https://news.ycombinator.com/item?id=50181667", "by": "yisraelgottz", "date": "2026-10-21", "stance": "recommend", "quote": "I think ElevenLabs clears.", "excerpt": "Hey I think ElevenLabs clears. I use PocketTTS for Memoe (https://github.com/memoe-app/memoe)", "context": "", "use_case": "voice cloning and TTS", "switched_from": "", "story": "Gemini vs. ElevenLabs Voice Cloning and TTS"}, {"id": 798105826, "item_id": 49881614, "url": "https://news.ycombinator.com/item?id=49881614", "by": "scosman", "date": "2026-09-28", "stance": "neutral", "quote": "can generate voiceover with elevenlabs", "excerpt": "These AI explainers are taking over. I tried getting this working back in May. The models were okay but not quite there and it was a ton of effort. Opus 5.5 seems like the tipping point. I made an OSS framework for these for when you want to go beyond one-shoting it: https://github.com/scosman/videowright - Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and ", "context": "", "use_case": "voiceover generation", "switched_from": "", "story": "Show HN: HN.watch \u2013 Videos of all Hacker News posts"}, {"id": 797428993, "item_id": 49839312, "url": "https://news.ycombinator.com/item?id=49839312", "by": "scosman", "date": "2026-09-25", "stance": "neutral", "quote": "can generate voiceover with elevenlabs", "excerpt": "I have an OSS framework for this: https://github.com/scosman/videowright - Voiceovers: aligns animations to the voiceover, can generate voiceover with elevenlabs, or will transcribe and timestamp a real voiceover - can reorder scenes both in code, and using ffmpeg for audio. - interactive controls during authoring, can ask for micro edits or re-builds - MP4 export/encoder - Generates the video with agent of your choi", "context": "", "use_case": "voiceover generation", "switched_from": "", "story": "Opus 5.5 is good at explainer videos"}, {"id": 794495377, "item_id": 49655961, "url": "https://news.ycombinator.com/item?id=49655961", "by": "adityashankar", "date": "2026-09-11", "stance": "warn", "quote": "I tried it with elevenlabs before but it wasn't live enough and the models were not intelligent enough.", "excerpt": "Oh yeah, I built so much stuff to learn German, for example [1] to give me random German texts, force me to read it, and answer it, I created [2] to automatically make flashcards for me and then use with with a flashcards app I regularly use and [3] to help me memorise German cases and word-genders. I love it! I did think of implementing this conversationally, but tbh it has always been too expensive thus far, I gott", "context": "learning German", "use_case": "conversational language practice", "switched_from": "", "story": "GPT\u2011Live\u20111 in the API"}, {"id": 792964561, "item_id": 49560285, "url": "https://news.ycombinator.com/item?id=49560285", "by": "MitziMoto", "date": "2026-09-04", "stance": "neutral", "quote": "On the ElevenLabs platform, you provide them a system prompt", "excerpt": "We use a Twilio integration to make it work over a real phone line, but it could just as well be an app or websocket connection in a browser. Voice transport medium aside, the actual use case is not quite what you described. Companies like Eleven Labs and Vapi provide a full end to end voice agent platform. They handle the STT -> LLM -> TTS pipeline and infrastructure for voice agents. Think of a customer talking to ", "context": "", "use_case": "voice agent platform", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}, {"id": 792961904, "item_id": 49560119, "url": "https://news.ycombinator.com/item?id=49560119", "by": "MitziMoto", "date": "2026-09-04", "stance": "neutral", "quote": "point any voice agent platform we choose -- eleven labs, vapi, pipecat, whatever", "excerpt": "We use MCP in production for our customer facing voice agents. Our custom MCP server defines tools and resources that the voice agents need access to to interact with our customers. (E.g. scheduling appointments, checking order status, etc). Now we can point any voice agent platform we choose -- eleven labs, vapi, pipecat, whatever -- at our custom MCP server and it instantly has an understanding of the tools availab", "context": "", "use_case": "customer-facing voice agents", "switched_from": "", "story": "Ask HN: Who is using MCP in production?"}, {"id": 790486112, "item_id": 49405382, "url": "https://news.ycombinator.com/item?id=49405382", "by": "dannyw", "date": "2026-08-23", "stance": "recommend", "quote": "11labs does _way_ more than basic TTS.", "excerpt": "11labs does _way_ more than basic TTS. The options, customizability, quality of voice cloning (for editing your own voices), etc is far more than what you see on the surface. Check out their docs for a glimpse: https://elevenlabs.io/docs/api-reference/introduction If you wanna hook up a voice agent to Twilio for support for example, 11labs is probably one of the quickest and least painful ways to integrate while stil", "context": "", "use_case": "voice agents, TTS, voice cloning", "switched_from": "", "story": "ElevenLabs, TwelveLabs, ThirteenLabs"}, {"id": 787698993, "item_id": 49231187, "url": "https://news.ycombinator.com/item?id=49231187", "by": "thepoet", "date": "2026-08-09", "stance": "neutral", "quote": "generate audiobooks on topics I want to understand with ElevenLabs, Exa and OpenAI", "excerpt": "I have a Kobo that was kept unused in a similar state for a few years until I decide to build an SDK platform to develop and deploy apps on it. My Kobo does not support apps on its Linux platform. I have been using it to read HN, as an RSS reader over my news and blog sources, generate audiobooks on topics I want to understand with ElevenLabs, Exa and OpenAI and listen via connecting its bluetooth to my speakers and ", "context": "", "use_case": "generating audiobooks", "switched_from": "", "story": "Reviving a four year old reMarkable 2"}, {"id": 786551443, "item_id": 49159465, "url": "https://news.ycombinator.com/item?id=49159465", "by": "thepoet", "date": "2026-08-03", "stance": "neutral", "quote": "an audiobook generator using deep research and ElevenLabs API", "excerpt": "A bit idealistic for the crowd here but has some good points. The other day I wanted to build personal apps for my Kobo device. It has a single ~800Mhz core and 512 MB of RAM, probably eight times less than a rasbperry pi, but runs a Linux. I wanted to break free from watching my laptop screen for long Claude sessions partially due to degrading eyesight and have a sidekick for approvals streamed to the Kobo. Apart fr", "context": "", "use_case": "audiobook generation", "switched_from": "", "story": "Devtools must be open source"}, {"id": 785341888, "item_id": 49083868, "url": "https://news.ycombinator.com/item?id=49083868", "by": "wrsh07", "date": "2026-07-28", "stance": "neutral", "quote": "I listened to some books from standard ebooks using eleven labs", "excerpt": "This is great! I would love an explicit \"set bookmark to here\" button if I scroll up from the high watermark I discovered the reset, but it took a minute and I expect given the way I read being able to explicitly walk the high watermark back a bit would be nice (maybe that's doable if you select text? I didn't try!) The format is nice, I love standard ebooks I opened Moby Dick but didn't see how to listen to it on my", "context": "", "use_case": "text-to-speech audiobooks", "switched_from": "", "story": "Show HN: tale.fyi, we deserve a home for fiction"}, {"id": 781203649, "item_id": 48825228, "url": "https://news.ycombinator.com/item?id=48825228", "by": "rnxrx", "date": "2026-07-07", "stance": "compare", "quote": "Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well", "excerpt": "Another endorsement - I used Kokoro pretty extensively with an app I was developing over the last year and it's been excellent, both on- and off- GPU. Even with Elevenlabs (long time subscriber) the comparative quality of Kokoro keeps up really well until you get to their larger models with their professional voices. I do wish there were better support for SSML, as well as deeper documentation of how to influence inf", "context": "", "use_case": "TTS", "switched_from": "", "story": "Local, CPU-Friendly, High-Quality TTS (Text-to-Speech) with Kokoro"}, {"id": 778736032, "item_id": 48671002, "url": "https://news.ycombinator.com/item?id=48671002", "by": "Protostome", "date": "2026-06-25", "stance": "neutral", "quote": "I ran it through ElevenLabs transcription and GPT5.5 based translation of the transcript", "excerpt": "Did you encounter any mistranslation here specifically? it's pretty easy to translate the video with Gemini or a different AI tool. I did it - I ran it through ElevenLabs transcription and GPT5.5 based translation of the transcript, this is what I got: 00:00:16,479 --> 00:00:34,520 [Speaker 0] And I pray in every prayer \u2014 every prayer, every prayer \u2014 that I, your father, your sisters, girls and boys, all of you, will", "context": "", "use_case": "audio transcription", "switched_from": "", "story": "Israel targeted Gaza children resulting in genocide, UN inquiry says"}, {"id": 763480481, "item_id": 47717530, "url": "https://news.ycombinator.com/item?id=47717530", "by": "Areena_28", "date": "2026-04-10", "stance": "recommend", "quote": "Eleven Labs made voiceover work that used to cost thousands into a $5 task", "excerpt": "The disruption is 101% happening but it's mostly invisible from the outside. iI think its not new apps replacing old ones rather the same apps doing things that used to require 3x the headcount. That said there are a few genuine examples Cursor basically replaced how a lot of developers write code, Eleven Labs made voiceover work that used to cost thousands into a $5 task, and Gamma turned presentations from a half-d", "context": "", "use_case": "voiceover", "switched_from": "", "story": "Ask HN: Where are all the disruptive software that AI promised?"}, {"id": 755636947, "item_id": 47227309, "url": "https://news.ycombinator.com/item?id=47227309", "by": "suganesh95", "date": "2026-03-02", "stance": "neutral", "quote": "elevenlabs for STT", "excerpt": "I built something very similar and comparble to this with wakeword detection on my raaberry pi. Groq 8b instant is the fastest llm from my test. I used smallest ai for tts as it has the smallest TTFT My rasberry pi stack: porcupine for wakeword detection + elevenlabs for STT + groq scout as it supports home automation better + smallest.ai for 70ms ttfb Call stack: twilio + groq whisper for STT + groq 8b instant + sma", "context": "", "use_case": "speech-to-text", "switched_from": "", "story": "Show HN: I built a sub-500ms latency voice agent from scratch"}, {"id": 755577746, "item_id": 47223609, "url": "https://news.ycombinator.com/item?id=47223609", "by": "arbayi", "date": "2026-03-02", "stance": "neutral", "quote": "We used LemonSlice, LiveKit, and ElevenLabs.", "excerpt": "For a fun side project, we built a quick demo to interview our OpenClaw agent called Mahmut. We used LemonSlice, LiveKit, and ElevenLabs. We just shared the full interview, and here's the repo if anyone is interested in building the same thing: https://github.com/openserv-labs/openclaw-voice-avatar Our avatar was a really hard one to handle, but I think it's still really good. All we did was connect the APIs. LemonSl", "context": "", "use_case": "voice synthesis", "switched_from": "", "story": "We Interviewed Our OpenClaw Agent Using a Voice Avatar"}, {"id": 747830992, "item_id": 46739437, "url": "https://news.ycombinator.com/item?id=46739437", "by": "Johnny_Bonk", "date": "2026-01-23", "stance": "recommend", "quote": "use eleven labs api which is pretty generous", "excerpt": "Nice I'll try it, as of now for my personal stt workflow I use eleven labs api which is pretty generous but curious to play around with other options", "context": "", "use_case": "speech-to-text workflow", "switched_from": "", "story": "Ask HN: What's the current best local/open speech-to-speech setup?"}, {"id": 744828896, "item_id": 46551806, "url": "https://news.ycombinator.com/item?id=46551806", "by": "Mashimo", "date": "2026-01-09", "stance": "recommend", "quote": "If you want to get real good quality TTS, you should check out elevenlabs.io", "excerpt": "Here is an overview: https://www.inferless.com/learn/comparing-different-text-to-speech---tts--models-part-2 Also keep in mind the processing time. The ^ article above used a NVIDIA L4 with 24-GB VRAM. Sopro claims 7.5 second processing time on CPU for 30 seconds of audio! If you want to get real good quality TTS, you should check out elevenlabs.io Different tools for different goals.", "context": "", "use_case": "high-quality text-to-speech", "switched_from": "", "story": "Sopro TTS: A 169M model with zero-shot voice cloning that runs on the CPU"}, {"id": 733492273, "item_id": 45843267, "url": "https://news.ycombinator.com/item?id=45843267", "by": "tptacek", "date": "2025-11-06", "stance": "neutral", "quote": "synthesized with ElevenLabs", "excerpt": "I recently bought a mint-condition Alf phone, in the shape of Gordon Shumway of TV's \"Alf\", out of the back of an old auto shop in the south suburbs of Chicago, and naturally did the most obvious thing, which was to make a Gordon Shumway phone that has conversations in the voice of Gordon Shumway (sampled from Youtube and synthesized with ElevenLabs). I use https://github.com/etalab-ia/faster-whisper-server (I think?", "context": "", "use_case": "voice synthesis", "switched_from": "", "story": "You should write an agent"}]}