Hey Product Hunt 👋 Thrilled to introduce Parrot, Ringg’s speech-to-text model built for production-grade voice agents. Most STT models do well on clean audio. Voice agents don’t get clean audio. They deal with compressed phone calls, Hindi-English code-switching, Indian accents, background noise, and conversations where one misheard word can break the next action. What makes it different: 🦜 Built for real world calls 🦜 Low latency inference for smoother voice agent conversations 🦜 Hindi validation and normalization for cleaner downstream workflows 🦜 Strong Normalised WER performance on open-source Hindi benchmarks For teams building voice agents, Parrot helps turn messy speech into cleaner transcripts that LLMs can actually use. Try it out and let us know what you're building with it!
Human Signal
创始人 / Maker 评论
优先展示 Product Hunt 上对理解条目有帮助的人类文本。
Topics
APIArtificial IntelligenceAudio
痛点分析发布于 2026/05/26
痛点为 AI 基于上游原始证据的初步提炼；未包含额外中国市场检索。
痛点
在构建生产级语音助手时，开发者面临的核心痛点在于现有语音转文字模型在真实通话场景下表现不佳。产品描述和用户评论均指出，大多数STT模型在干净音频上表现良好，但语音助手实际处理的是压缩电话、印地语-英语混合、印度口音、背景噪音等复杂音频，一个词听错就可能导致后续动作失败。用户提到，通用STT API在代码切换和地区口音上容易崩溃，原始转录文本噪声过大，无法用于可靠的意图解析。此外，多人对话中的重叠语音、打断和接话场景也是难点，现有模型在此类情况下质量严重下降。这导致开发者需要额外投入大量精力进行音频预处理、转录后验证和错误修复，增加了开发周期和运维成本，且难以保证下游LLM能获得足够干净的输入。
Discussion
精选 Product Hunt 讨论
保留原始讨论语境，用来交叉验证上游条目的真实反馈。
Congrats on the launch! Building voice sessions into a couples app right now (currently on Deepgram for streaming transcription), so the "voice agents don't get clean audio" framing really lands...clean-audio benchmarks oversell every STT model until you hit a real room. One thing I've run into that I'd love your take on: the hardest case isn't accent or noise, it's two people talking , overlapping speech, interruptions, one person finishing the other's sentence. Most STT degrades badly there. Is Parrot tuned mainly for the single-caller voice-agent case (one human, one agent), or does it hold up on genuine multi-speaker conversations? Curious whether that's a roadmap item or a deliberate scope line.
Building a dedicated validation layer for Hindi downstream workflows is clever. Most generic STT APIs fall apart on code-switching and regional accents. We've hit similar walls where raw transcripts were too noisy for reliable intent parsing in production pipelines. How do you handle Hinglish code-switching, and what's the P95 latency on a 10-second audio chunk?
Our AI has a voice mode. We use ChatGPT (before that, we used speech-to-text recognition and then text-to-speech). How is your service better? Is it only better Hindi recognition, or is there something else?
Haha, how can something be this useful and this scary simultaneously!? As someone with a name most humans can't spell right, I look forward to the day when this is no longer an issue.
源数据· Raw Archive
- source
- Product Hunt
- upstream_source
- producthunt_api
- upstream_item_id
- 1155711
- daily_ranking_item_id
- 650757ae-5303-42d4-816e-6e408f208061
- rank_date
- 2026-05-26
- rank
- 5
- name
- Parrot Speech-to-text API
- tagline
- Fast, accurate STT for production-grade voice agents
- description
- Introducing Parrot: Ringg’s speech-to-text model for production-grade voice agents. Capture Hindi-heavy and noisy real-world conversations with low-latency inference, stronger transcript quality, and Hindi validation built for downstream workflows.
- maker_comment
- <p>Hey Product Hunt 👋<br><br>Thrilled to introduce Parrot, <a href="https://www.ringg.ai/" target="_blank" rel="nofollow noopener noreferrer">Ringg’s</a> speech-to-text model built for production-grade voice agents.<br><br>Most STT models do well on clean audio. Voice agents don’t get clean audio. They deal with compressed phone calls, Hindi-English code-switching, Indian accents, background noise, and conversations where one misheard word can break the next action.<br><br>What makes it different:<br><br>🦜 Built for real world calls<br>🦜 Low latency inference for smoother voice agent conversations<br>🦜 Hindi validation and normalization for cleaner downstream workflows<br>🦜 Strong Normalised WER performance on open-source Hindi benchmarks<br><br>For teams building voice agents, Parrot helps turn messy speech into cleaner transcripts that LLMs can actually use.<br><br><a href="https://www.ringg.ai/models/speech-to-text/v1" target="_blank" rel="nofollow noopener noreferrer">Try it out</a> and let us know what you're building with it!</p>
- votes_count
- 152
- comments_count
- 19
- reviews_count
- 1
- featured_at
- 2026-05-26T07:01:00.000Z
- created_at_on_source
- 2026-05-26T07:01:00.000Z
makers
item-1item-2item-3item-4
topics
APIArtificial IntelligenceAudio
media / source-specific data
[
{
"url": "https://ph-files.imgix.net/560c5ac6-5e86-4314-8355-ddcaf4b7f222.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/17e91259-1168-44ca-b511-e645fc2f1a92.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/dbf64a16-dd6e-43e0-8d37-940e3dcc9445.jpeg?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/863e567b-e2d1-4251-bbbc-f20f2d8e8c79.jpeg?auto=format",
"type": "video",
"videoUrl": "https://youtu.be/9HdN_GLXm_Y"
}
]raw_payload
{
"post_id": "1155711",
"fetched_at": "2026-05-26T22:00:01.964Z",
"has_post_detail": true,
"snapshot_version": "producthunt_v1",
"has_maker_comment": true,
"maker_comment_source": "maker_match",
"comments_fetch_status": "ok",
"selected_comment_count": 5
}source_raw_snapshot
{
"id": "0df31135-37f2-4ac8-9106-34e871b2a53c",
"daily_ranking_item_id": "650757ae-5303-42d4-816e-6e408f208061",
"source": "producthunt_api",
"product_hunt_id": "1155711",
"fetched_at": "2026-05-26T22:00:01.964Z",
"post_raw": {
"id": "1155711",
"url": "https://www.producthunt.com/products/parrot-speech-to-text-api?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"name": "Parrot Speech-to-text API",
"media": [
{
"url": "https://ph-files.imgix.net/560c5ac6-5e86-4314-8355-ddcaf4b7f222.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/17e91259-1168-44ca-b511-e645fc2f1a92.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/dbf64a16-dd6e-43e0-8d37-940e3dcc9445.jpeg?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/863e567b-e2d1-4251-bbbc-f20f2d8e8c79.jpeg?auto=format",
"type": "video",
"videoUrl": "https://youtu.be/9HdN_GLXm_Y"
}
],
"tagline": "Fast, accurate STT for production-grade voice agents",
"thumbnail": {
"url": "https://ph-files.imgix.net/8a251e51-a9c9-48f2-93dd-42474cc29f1a.png?auto=format"
},
"votesCount": 152,
"description": "Introducing Parrot: Ringg’s speech-to-text model for production-grade voice agents. Capture Hindi-heavy and noisy real-world conversations with low-latency inference, stronger transcript quality, and Hindi validation built for downstream workflows."
},
"post_detail_raw": {
"id": "1155711",
"slug": "parrot-speech-to-text-api",
"user": {
"id": "4712617",
"url": "https://www.producthunt.com/@itsmeparth?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"name": "Parth Chadha",
"headline": "Growth @ Ringg AI",
"username": "itsmeparth",
"websiteUrl": "https://www.linkedin.com/in/itsme-parth/",
"profileImage": "https://ph-avatars.imgix.net/4712617/8d468bac-6c27-4e1c-9c41-b01ff40064fa.jpeg?auto=format&crop=faces&fit=crop&h=original&w=original",
"twitterUsername": null
},
"media": [
{
"url": "https://ph-files.imgix.net/560c5ac6-5e86-4314-8355-ddcaf4b7f222.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/17e91259-1168-44ca-b511-e645fc2f1a92.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/dbf64a16-dd6e-43e0-8d37-940e3dcc9445.jpeg?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/863e567b-e2d1-4251-bbbc-f20f2d8e8c79.jpeg?auto=format",
"type": "video",
"videoUrl": "https://youtu.be/9HdN_GLXm_Y"
}
],
"makers": [
{
"id": "0",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"websiteUrl": null,
"profileImage": null,
"twitterUsername": null
},
{
"id": "0",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"websiteUrl": null,
"profileImage": null,
"twitterUsername": null
},
{
"id": "0",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"websiteUrl": null,
"profileImage": null,
"twitterUsername": null
},
{
"id": "0",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"websiteUrl": null,
"profileImage": null,
"twitterUsername": null
}
],
"topics": {
"edges": [
{
"node": {
"id": "88",
"name": "API",
"slug": "api-1"
}
},
{
"node": {
"id": "268",
"name": "Artificial Intelligence",
"slug": "artificial-intelligence"
}
},
{
"node": {
"id": "471",
"name": "Audio",
"slug": "audio"
}
}
]
},
"website": "https://www.producthunt.com/r/IX5OZ7CV6SI4OU?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"createdAt": "2026-05-26T07:01:00Z",
"dailyRank": 5,
"thumbnail": {
"url": "https://ph-files.imgix.net/8a251e51-a9c9-48f2-93dd-42474cc29f1a.png?auto=format",
"type": "image",
"videoUrl": null
},
"featuredAt": "2026-05-26T07:01:00Z",
"weeklyRank": 12,
"yearlyRank": null,
"monthlyRank": 471,
"scheduledAt": "2026-05-26T07:01:00Z",
"productLinks": [
{
"url": "https://www.producthunt.com/r/SQNGLAFA4LE2YH?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"type": "LinkedIn"
},
{
"url": "https://www.producthunt.com/r/JOHJCWCZLIZJ3R?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"type": "Website"
},
{
"url": "https://www.producthunt.com/r/BYIHU64VTILSZ6?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"type": "Twitter"
},
{
"url": "https://www.producthunt.com/r/IX5OZ7CV6SI4OU?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"type": "Website"
}
],
"reviewsCount": 1,
"commentsCount": 19,
"reviewsRating": 5
},
"maker_comment_raw": {
"id": "5400835",
"url": "https://www.producthunt.com/products/parrot-speech-to-text-api?comment=5400835&utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"body": "<p>Hey Product Hunt 👋<br><br>Thrilled to introduce Parrot, <a href=\"https://www.ringg.ai/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Ringg’s</a> speech-to-text model built for production-grade voice agents.<br><br>Most STT models do well on clean audio. Voice agents don’t get clean audio. They deal with compressed phone calls, Hindi-English code-switching, Indian accents, background noise, and conversations where one misheard word can break the next action.<br><br>What makes it different:<br><br>🦜 Built for real world calls<br>🦜 Low latency inference for smoother voice agent conversations<br>🦜 Hindi validation and normalization for cleaner downstream workflows<br>🦜 Strong Normalised WER performance on open-source Hindi benchmarks<br><br>For teams building voice agents, Parrot helps turn messy speech into cleaner transcripts that LLMs can actually use.<br><br><a href=\"https://www.ringg.ai/models/speech-to-text/v1\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Try it out</a> and let us know what you're building with it!</p>",
"user": {
"id": "4712617",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profile_url": "[REDACTED]",
"website_url": null,
"profile_image": null,
"twitter_username": null
},
"user_id": "4712617",
"is_maker": true,
"parent_id": null,
"created_at": "2026-05-25T19:49:35Z",
"replies_raw": [],
"votes_count": 19
},
"selected_comments_raw": [
{
"id": "5400835",
"url": "https://www.producthunt.com/products/parrot-speech-to-text-api?comment=5400835&utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"body": "<p>Hey Product Hunt 👋<br><br>Thrilled to introduce Parrot, <a href=\"https://www.ringg.ai/\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Ringg’s</a> speech-to-text model built for production-grade voice agents.<br><br>Most STT models do well on clean audio. Voice agents don’t get clean audio. They deal with compressed phone calls, Hindi-English code-switching, Indian accents, background noise, and conversations where one misheard word can break the next action.<br><br>What makes it different:<br><br>🦜 Built for real world calls<br>🦜 Low latency inference for smoother voice agent conversations<br>🦜 Hindi validation and normalization for cleaner downstream workflows<br>🦜 Strong Normalised WER performance on open-source Hindi benchmarks<br><br>For teams building voice agents, Parrot helps turn messy speech into cleaner transcripts that LLMs can actually use.<br><br><a href=\"https://www.ringg.ai/models/speech-to-text/v1\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Try it out</a> and let us know what you're building with it!</p>",
"user": {
"id": "4712617",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profile_url": "[REDACTED]",
"website_url": null,
"profile_image": null,
"twitter_username": null
},
"user_id": "4712617",
"is_maker": true,
"parent_id": null,
"created_at": "2026-05-25T19:49:35Z",
"replies_raw": [],
"votes_count": 19,
"selection_score": 400,
"selection_reason": "maker_comment"
},
{
"id": "5402626",
"url": "https://www.producthunt.com/products/parrot-speech-to-text-api?comment=5402626&utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"body": "<p>Congrats on the launch! Building voice sessions into a couples app right now (currently on Deepgram for streaming transcription), so the \"voice agents don't get clean audio\" framing really lands...clean-audio benchmarks oversell every STT model until you hit a real room. One thing I've run into that I'd love your take on: the hardest case isn't accent or noise, it's <em>two people talking</em>, overlapping speech, interruptions, one person finishing the other's sentence. Most STT degrades badly there. Is Parrot tuned mainly for the single-caller voice-agent case (one human, one agent), or does it hold up on genuine multi-speaker conversations? Curious whether that's a roadmap item or a deliberate scope line.</p>",
"user": {
"id": "2410943",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profile_url": "[REDACTED]",
"website_url": null,
"profile_image": null,
"twitter_username": null
},
"user_id": "2410943",
"is_maker": false,
"parent_id": null,
"created_at": "2026-05-26T11:38:55Z",
"replies_raw": [],
"votes_count": 2,
"selection_score": 400,
"selection_reason": "body_signal_score"
},
{
"id": "5402635",
"url": "https://www.producthunt.com/products/parrot-speech-to-text-api?comment=5402635&utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"body": "<p>Building a dedicated validation layer for Hindi downstream workflows is clever. Most generic STT APIs fall apart on code-switching and regional accents. We've hit similar walls where raw transcripts were too noisy for reliable intent parsing in production pipelines. How do you handle Hinglish code-switching, and what's the P95 latency on a 10-second audio chunk?</p>",
"user": {
"id": "9825328",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profile_url": "[REDACTED]",
"website_url": null,
"profile_image": null,
"twitter_username": null
},
"user_id": "9825328",
"is_maker": false,
"parent_id": null,
"created_at": "2026-05-26T11:43:03Z",
"replies_raw": [],
"votes_count": 1,
"selection_score": 371,
"selection_reason": "body_signal_score"
},
{
"id": "5403148",
"url": "https://www.producthunt.com/products/parrot-speech-to-text-api?comment=5403148&utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"body": "<p>Our AI has a voice mode. We use ChatGPT (before that, we used speech-to-text recognition and then text-to-speech). How is your service better? Is it only better Hindi recognition, or is there something else?</p>",
"user": {
"id": "9211339",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profile_url": "[REDACTED]",
"website_url": null,
"profile_image": null,
"twitter_username": null
},
"user_id": "9211339",
"is_maker": false,
"parent_id": null,
"created_at": "2026-05-26T14:27:13Z",
"replies_raw": [],
"votes_count": 1,
"selection_score": 214,
"selection_reason": "body_signal_score"
},
{
"id": "5401830",
"url": "https://www.producthunt.com/products/parrot-speech-to-text-api?comment=5401830&utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"body": "<p>Haha, how can something be this useful and this scary simultaneously!? As someone with a name most humans can't spell right, I look forward to the day when this is no longer an issue.</p>",
"user": {
"id": "3658931",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profile_url": "[REDACTED]",
"website_url": null,
"profile_image": null,
"twitter_username": null
},
"user_id": "3658931",
"is_maker": false,
"parent_id": null,
"created_at": "2026-05-26T07:49:53Z",
"replies_raw": [],
"votes_count": 7,
"selection_score": 190,
"selection_reason": "body_signal_score"
}
],
"topics_raw": [
{
"id": "88",
"name": "API",
"slug": "api-1"
},
{
"id": "268",
"name": "Artificial Intelligence",
"slug": "artificial-intelligence"
},
{
"id": "471",
"name": "Audio",
"slug": "audio"
}
],
"makers_raw": [
{
"id": "0",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profileUrl": "[REDACTED]",
"websiteUrl": null,
"profileImage": null,
"twitterUsername": null
},
{
"id": "0",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profileUrl": "[REDACTED]",
"websiteUrl": null,
"profileImage": null,
"twitterUsername": null
},
{
"id": "0",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profileUrl": "[REDACTED]",
"websiteUrl": null,
"profileImage": null,
"twitterUsername": null
},
{
"id": "0",
"url": "[REDACTED]",
"name": "[REDACTED]",
"headline": null,
"username": "[REDACTED]",
"profileUrl": "[REDACTED]",
"websiteUrl": null,
"profileImage": null,
"twitterUsername": null
}
],
"launch_metadata_raw": {
"slug": "parrot-speech-to-text-api",
"daily_rank": 5,
"featured_at": "2026-05-26T07:01:00Z",
"website_url": "https://www.producthunt.com/r/IX5OZ7CV6SI4OU?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"weekly_rank": 12,
"yearly_rank": null,
"monthly_rank": 471,
"scheduled_at": "2026-05-26T07:01:00Z",
"reviews_rating": 5,
"created_at_on_product_hunt": "2026-05-26T07:01:00Z"
},
"stats_raw": {
"votes_count": 152,
"reviews_count": 1,
"comments_count": 19,
"reviews_rating": 5
},
"aux_raw": {
"media_extended": [
{
"url": "https://ph-files.imgix.net/560c5ac6-5e86-4314-8355-ddcaf4b7f222.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/17e91259-1168-44ca-b511-e645fc2f1a92.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/dbf64a16-dd6e-43e0-8d37-940e3dcc9445.jpeg?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/863e567b-e2d1-4251-bbbc-f20f2d8e8c79.jpeg?auto=format",
"type": "video",
"videoUrl": "https://youtu.be/9HdN_GLXm_Y"
}
],
"submitter_user": {
"id": "4712617",
"url": "https://www.producthunt.com/@itsmeparth?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"name": "Parth Chadha",
"headline": "Growth @ Ringg AI",
"username": "itsmeparth",
"profileUrl": "https://www.producthunt.com/@itsmeparth?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"websiteUrl": "https://www.linkedin.com/in/itsme-parth/",
"profileImage": "https://ph-avatars.imgix.net/4712617/8d468bac-6c27-4e1c-9c41-b01ff40064fa.jpeg?auto=format&crop=faces&fit=crop&h=original&w=original",
"twitterUsername": null
},
"presentation_only": {
"thumbnail_url": "https://ph-files.imgix.net/8a251e51-a9c9-48f2-93dd-42474cc29f1a.png?auto=format",
"product_hunt_url": "https://www.producthunt.com/products/parrot-speech-to-text-api?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"product_hunt_slug": "parrot-speech-to-text-api"
},
"unused_upstream_fields": {
"post_aux": {},
"comments_aux": {},
"post_detail_aux": {
"media_raw": [
{
"url": "https://ph-files.imgix.net/560c5ac6-5e86-4314-8355-ddcaf4b7f222.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/17e91259-1168-44ca-b511-e645fc2f1a92.png?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/dbf64a16-dd6e-43e0-8d37-940e3dcc9445.jpeg?auto=format",
"type": "image",
"videoUrl": null
},
{
"url": "https://ph-files.imgix.net/863e567b-e2d1-4251-bbbc-f20f2d8e8c79.jpeg?auto=format",
"type": "video",
"videoUrl": "https://youtu.be/9HdN_GLXm_Y"
}
],
"thumbnail_raw": {
"url": "https://ph-files.imgix.net/8a251e51-a9c9-48f2-93dd-42474cc29f1a.png?auto=format",
"type": "image",
"videoUrl": null
},
"presentation_only": {
"product_hunt_slug": "parrot-speech-to-text-api"
},
"product_links_raw": [
{
"url": "https://www.producthunt.com/r/SQNGLAFA4LE2YH?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"type": "LinkedIn"
},
{
"url": "https://www.producthunt.com/r/JOHJCWCZLIZJ3R?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"type": "Website"
},
{
"url": "https://www.producthunt.com/r/BYIHU64VTILSZ6?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"type": "Twitter"
},
{
"url": "https://www.producthunt.com/r/IX5OZ7CV6SI4OU?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"type": "Website"
}
],
"submitter_user_raw": {
"id": "4712617",
"url": "https://www.producthunt.com/@itsmeparth?utm_campaign=producthunt-api&utm_medium=api-v2&utm_source=Application%3A+jingx+%28ID%3A+278031%29",
"name": "Parth Chadha",
"headline": "Growth @ Ringg AI",
"username": "itsmeparth",
"websiteUrl": "https://www.linkedin.com/in/itsme-parth/",
"profileImage": "https://ph-avatars.imgix.net/4712617/8d468bac-6c27-4e1c-9c41-b01ff40064fa.jpeg?auto=format&crop=faces&fit=crop&h=original&w=original",
"twitterUsername": null
},
"unused_upstream_fields": {}
}
}
},
"selection_meta": {
"scoring_basis": "maker first, then non-maker body signal score with original order tie-break",
"first_comment_id": "5400835",
"comments_strategy": "maker_plus_top_discussion",
"detail_fetch_status": "ok",
"top_candidate_count": 10,
"maker_comment_source": "maker_match",
"comments_fetch_status": "ok",
"dropped_comment_count": 5,
"comments_fetched_limit": 25,
"newest_candidate_count": 10,
"selected_comment_count": 5,
"candidate_comment_count": 10,
"selected_comment_reasons": [
{
"id": "5400835",
"score": 400,
"reason": "maker_comment"
},
{
"id": "5402626",
"score": 400,
"reason": "body_signal_score"
},
{
"id": "5402635",
"score": 371,
"reason": "body_signal_score"
},
{
"id": "5403148",
"score": 214,
"reason": "body_signal_score"
},
{
"id": "5401830",
"score": 190,
"reason": "body_signal_score"
}
]
},
"created_at": "2026-05-26T22:00:10.432Z",
"updated_at": "2026-05-26T22:00:10.432Z"
}