{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-07-23T06:40:50.084Z","headline":"OpenRouter 新增音频转写 API，支持 Whisper 与 token 计价 STT 模型","description":"OpenRouter 推出 POST /api/v1/audio/transcriptions 端点，用户可使用同一 API key 将 base64 编码音频发送至该端点，返回 JSON 格式文本与用量对象。","url":"https://www.aioga.com/news/cmrvo24p604bvbihbk4aexnv6/","mainEntityOfPage":"https://www.aioga.com/news/cmrvo24p604bvbihbk4aexnv6/","datePublished":"2026-07-22T00:00:00.000Z","dateModified":"2026-07-22T00:00:00.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://openrouter.ai/blog/tutorials/transcription-on-openrouter","https://aihot.virxact.com/items/cmrvo24p604bvbihbk4aexnv6"],"canonicalUrl":"https://www.aioga.com/news/cmrvo24p604bvbihbk4aexnv6/","directAnswer":{"@type":"Answer","text":"OpenRouter 新增音频转写端点 POST /api/v1/audio/transcriptions。用户可沿用 Chat Completions 的 API key 与认证方式，提交 base64 编码音频，并在单次响应中获得转写文本及用量对象。","url":"https://www.aioga.com/news/cmrvo24p604bvbihbk4aexnv6/","dateCreated":"2026-07-22T00:00:00.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"openrouter.ai source article","url":"https://openrouter.ai/blog/tutorials/transcription-on-openrouter","datePublished":"2026-07-22T00:00:00.000Z","provider":{"@type":"Organization","name":"openrouter.ai","url":"https://openrouter.ai/blog/tutorials/transcription-on-openrouter"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmrvo24p604bvbihbk4aexnv6","datePublished":"2026-07-22T00:00:00.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmrvo24p604bvbihbk4aexnv6"}}],"aggregationSource":"OpenRouter：Announcements（RSS）","originalPublisher":{"name":"openrouter.ai","url":"https://openrouter.ai/blog/tutorials/transcription-on-openrouter"},"article":{"id":"cmrvo24p604bvbihbk4aexnv6","slug":"cmrvo24p604bvbihbk4aexnv6","url":"https://www.aioga.com/news/cmrvo24p604bvbihbk4aexnv6/","title":"OpenRouter 新增音频转写 API，支持 Whisper 与 token 计价 STT 模型","title_en":"Transcription on OpenRouter","summary":"OpenRouter 推出 POST /api/v1/audio/transcriptions 端点，用户可使用同一 API key 将 base64 编码音频发送至该端点，返回 JSON 格式文本与用量对象。","source":"OpenRouter：Announcements（RSS）","sourceUrl":"https://openrouter.ai/blog/tutorials/transcription-on-openrouter","aiHotUrl":"https://aihot.virxact.com/items/cmrvo24p604bvbihbk4aexnv6","publishedAt":"2026-07-22T00:00:00.000Z","category":"技巧观点","score":72,"selected":true,"articleBody":["You’ve got a 40-minute sales call recording, a folder of voice memos, or a user holding down a mic button, and you need a text transcript. The usual approach is to stand up a Whisper server or add a second provider SDK just for speech-to-text, on top of whatever already handles your chat traffic. On OpenRouter you can send the audio to POST /api/v1/audio/transcriptions instead and get back JSON with the transcribed text and a usage object, using the same API key and auth as Chat Completions.","You don’t need a new SDK or a separate service. Because transcription runs on the same platform as your chat traffic, a model hosted by several providers is load-balanced across them automatically instead of being pinned to a single vendor.","Send base64-encoded audio to POST /api/v1/audio/transcriptions and read the text field off the JSON response. You pass your OpenRouter API key as a Bearer token exactly as you do on a chat call, set a model, and hand it the audio.","The response is JSON with a text string that holds the transcript and a usage object that reports the audio duration in seconds, the token counts, and the dollar cost of the request. You make one request, and the transcript comes back in the response body, so there’s no polling and no job ID to track.","The request body carries a model and an input_audio object. Inside input_audio you put the file as base64 data and a format string. Optionally, you add a language hint, a temperature, and a provider block. Here it is end-to-end:","You can pick from two families of models. Whisper-class models like openai/whisper-1 ：https://openrouter.ai/docs/guides/overview/multimodal/stt are priced by duration, per second of audio, while newer speech-to-text models are priced per token. Which one fits depends on your accuracy bar, your language mix, and your budget.","STT model IDs don’t show up in the default /api/v1/models catalog. That’s expected, because transcription is an output modality you filter for.","That returns the speech-to-text models with their current per-model pricing. The same list lives in the Speech-to-Text collection：https://openrouter.ai/collections/speech-to-text-models if you’d rather read it as a page, and the model catalog：https://openrouter.ai/models carries live per-model rates.","If you want to try a model before you wire it up, the OpenRouter Playground：https://openrouter.ai/playground transcribes an uploaded file in-browser.","The whole flow takes three steps. You base64-encode the file, POST it with a model and a format, and read text and usage off the response. The data field takes raw base64 bytes, not a data: URI, so don’t prefix it with data:audio/mp3;base64, . The format field is required, and it tells the upstream model how to decode those bytes.","The endpoint also accepts OpenAI-style multipart/form-data uploads ( file plus model ), capped at 25 MB. If you already have a client built for OpenAI’s /v1/audio/transcriptions , you can point its base URL at https://openrouter.ai/api/v1 and it works unchanged. Files bigger than 25 MB go through the base64 JSON path.","A language hint is optional. If you leave it out, the model detects the language; setting it removes some ambiguity on short or noisy clips. Some providers accept their own extras through provider . Groq, for instance, takes a prompt for expected vocabulary via provider.options.groq.prompt , which helps with proper nouns and jargon the model would otherwise mangle.","The response is JSON with a text string and a usage object. The usage object is what lets you meter spend per request instead of estimating it.","That cost value is an example from our docs, not a price quote; your actual cost depends on the model and the audio length. The usage object reports seconds (audio duration), the token counts, and cost in dollars. The response also carries an X-Generation-Id header you can log to track or debug a specific request later.","Use /audio/transcriptions when you want audio turned into text, and audio input on chat when you want a model to reason about the audio.","The transcription endpoint fits meeting notes, voice commands, captioning, and searchable archives of calls or podcasts. If you want sentiment on a support call, a Q&A about what was said, or audio mixed with other modalities in one prompt, use the input_audio content type on /chat/completions . Turning text into speech is a third, separate endpoint.","For both audio analysis and text-to-speech, see the audio APIs announcement：https://openrouter.ai/blog/announcements/announcing-audio-apis.","Transcription uses the same routing layer as chat. When a model is hosted by more than one provider, we distribute your requests across them, load-balanced by price, so you aren’t pinned to a single vendor. What transcription doesn’t expose today is per-request routing control. The order , only , allow_fallbacks , data_collection , and sort fields you’d set on a chat call are not applied on /api/v1/audio/transcriptions . The provider block on this endpoint carries provider-specific options instead:","That request passes Groq a vocabulary hint for proper nouns it would otherwise mangle. The options are keyed by provider slug, and only the matched provider’s options are forwarded. If you need to pin a specific provider or enforce a per-request data policy on a transcription, that control isn’t available on this endpoint yet. The full provider object is documented in the provider routing docs：https://openrouter.ai/docs/guides/routing/provider-selection.","OpenRouter doesn’t mark up provider pricing：https://openrouter.ai/pricing, so the catalog rate is what you pay, and Zero Completion Insurance means a transcription that fails isn’t billed. If you already have a provider agreement, BYOK：https://openrouter.ai/docs/guides/overview/auth/byok lets you route through your own provider key and pay only our platform fee instead of the per-usage model cost, with the fee waived for the first 1M requests a month on pay-as-you-go.","Four constraints shape how you structure a transcription call:","Because the timeout caps processing time rather than audio length, a clip’s duration alone doesn’t tell you whether it will fit. A recording that runs for hours, like an overnight game session, needs the chunking treatment; a single call won’t cover it.","For captions, the default response is text plus usage with no timing. Set response_format to verbose_json and you get segment-level timestamps, plus word-level ones if you pass timestamp_granularities: [\"word\"] . That works on OpenAI-compatible providers (OpenAI, Groq, Together); other providers reject it with a 400. There’s no built-in .srt / .vtt output, so you build the subtitle file from the timestamps yourself.","You pay the model’s catalog rate with no markup from us, and the usage.cost field tells you the exact figure per request. Whisper-class models charge per second of audio, and newer models charge per token.","Rates change, so we keep the live figure on each model’s page in the catalog：https://openrouter.ai/models rather than printing one here. Reading usage.cost off the response tells you what each request actually cost. STT models are paid, so API transcription draws on your credit balance.","To get started, confirm a model fits your audio in the Playground：https://openrouter.ai/playground, wire up the call, and read usage.cost per request to meter spend from day one.","Send base64-encoded audio to POST /api/v1/audio/transcriptions with a model and an input_audio object ( data plus format ). The response is JSON with a text string (the transcript) and a usage object (seconds, tokens, and cost). It uses the same Bearer API key and auth as Chat Completions.","Yes. Whisper-class models are available for transcription, and openai/whisper-1 is the slug to use. STT model IDs aren’t in the default /api/v1/models list, so you discover them by filtering with ?output_modalities=transcription or browsing the Speech-to-Text collection：https://openrouter.ai/collections/speech-to-text-models. Whisper is duration-priced, per second of audio; newer STT models price per token instead.","The common set is wav , mp3 , flac , m4a , ogg , webm , and aac , passed in the required input_audio.format field. Support varies by model and provider, so not every model accepts every format. wav is the safest default for broad compatibility; compressed formats like mp3 give smaller, faster payloads.","Timestamps, yes. Set response_format to verbose_json to get segment-level timestamps, and add timestamp_granularities: [\"word\"] for word-level timestamps in a words array. That works on OpenAI-compatible providers (OpenAI, Groq, Together); other providers reject it with a 400. SRT/VTT output isn’t supported, so build subtitle files from the timestamps yourself.","The practical limit is the roughly 60-second upstream processing timeout, not a fixed audio-length cap. Short and medium clips return in one call. For long recordings, split the audio into segments, transcribe each, and stitch the text together.","You pay the model’s catalog rate with no markup. Whisper-class models price per second of audio; newer STT models price per token. The usage.cost field in each response reports the exact dollar cost of that request."],"articleImages":[{"sourceUrl":"https://openrouter.ai/blog/images/transcription-on-openrouter.png","alt":"Transcription on OpenRouter","afterParagraph":0,"url":"/media/articles/cmrvo24p604bvbihbk4aexnv6/78c6ecf127863446.png"},{"sourceUrl":"https://openrouter.ai/blog/images/transcription-request-flow.png","alt":"Three-step diagram of transcribing audio on OpenRouter: base64-encoded audio in the request body, POST /api/v1/audio/transcriptions with automatic load-balancing across providers, and a JSON response with text and usage fields","afterParagraph":3,"url":"/media/articles/cmrvo24p604bvbihbk4aexnv6/b076d0e68ecdc338.png"}],"mediaStatus":"ok","articleBodyZh":["你手上有一个40分钟的销售通话录音、一文件夹语音备忘录，或者一个用户按着麦克风按钮录音，你需要将其转成文字记录。常见方法是搭建一个Whisper服务器，或者在已有处理聊天流量的基础上，额外增加一个语音转文字的提供商SDK。在OpenRouter上，你可以将音频发送到POST /api/v1/audio/transcriptions，然后获取包含转录文本和使用情况对象的JSON，使用与聊天补全相同的API密钥和身份验证。","你不需要新的SDK或单独的服务。因为转录运行在与你的聊天流量相同的平台上，由多个提供商托管的模型会自动负载均衡，而不是绑定到单一供应商。","将base64编码的音频发送到POST /api/v1/audio/transcriptions，并从JSON响应中读取text字段。你像进行聊天调用一样，将OpenRouter API密钥作为Bearer令牌传递，设置一个模型，然后传入音频。","响应是一个JSON，其中text字符串包含转录内容，usage对象报告音频时长（秒）、token计数和请求花费。你只需发出一次请求，转录文本就会在响应体中返回，因此无需轮询，也无需跟踪作业ID。","请求体携带一个模型和一个input_audio对象。在input_audio内部，你放入文件的base64数据和格式字符串。可选地，你可以添加语言提示、temperature值和provider块。完整流程如下：","你可以选择两类模型。Whisper类模型，如openai/whisper-1：https://openrouter.ai/docs/guides/overview/multimodal/stt 按音频时长（每秒）计费，而新型语音转文字模型按token计费。适合哪种取决于你的准确率要求、语言组合和预算。","STT模型ID不会显示在默认的/api/v1/models目录中。这是预期之内的，因为转录是一种输出模式，需要过滤。","这样会返回语音转文字模型及其当前每模型定价。同样的列表也存在于Speech-to-Text集合中：https://openrouter.ai/collections/speech-to-text-models，如果你希望以页面形式查看，也可以在模型目录中：https://openrouter.ai/models 查阅实时每模型价格。","如果你想在连接模型之前先尝试一下，OpenRouter Playground：https://openrouter.ai/playground 可以在浏览器中转录上传的文件。","整个流程分三步。你需要将文件进行 base64 编码，然后与模型和格式一起 POST，并从响应中读取文本和使用情况。data 字段接受原始 base64 字节，而不是 data: URI，因此不要在前面加上 data:audio/mp3;base64,。format 字段是必需的，它告诉上游模型如何解码这些字节。","该端点也接受 OpenAI 风格的 multipart/form-data 上传（文件加模型），最大为 25 MB。如果你已经为 OpenAI 的 /v1/audio/transcriptions 构建了客户端，可以将其基础 URL 指向 https://openrouter.ai/api/v1，并且无需更改即可工作。大于 25 MB 的文件需要通过 base64 JSON 路径上传。","语言提示是可选的。如果你不提供，模型会检测语言；设置语言提示可以减少在短或嘈杂音频片段中的歧义。一些提供商通过 provider 接受自己的额外参数。例如 Groq，通过 provider.options.groq.prompt 提供预期词汇提示，这有助于处理模型可能会弄错的专有名词和术语。","响应是 JSON 格式，包含一个文本字符串和一个使用情况对象。使用情况对象让你可以按请求计量花费，而不是估算。","该成本值是我们文档中的示例，而非报价；你的实际费用取决于模型和音频长度。使用情况对象报告秒数（音频时长）、token 数量以及费用（美元）。响应还包含一个 X-Generation-Id 头，你可以记录它以便以后追踪或调试特定请求。","当你想将音频转换为文本时使用 /audio/transcriptions；当你希望模型分析音频时使用聊天的音频输入。","转录端点适合会议记录、语音指令、字幕以及可搜索的通话或播客档案。如果你想获取客服通话的情绪分析、关于所述内容的问答，或在一个提示中混合音频与其他模态的数据，请使用 /chat/completions 的 input_audio 内容类型。将文本转语音是第三个独立的端点。","关于音频分析和文本转语音，请参阅音频 API 公告：https://openrouter.ai/blog/announcements/announcing-audio-apis。","转录使用与聊天相同的路由层。当一个模型由多个提供商托管时，我们会根据价格在它们之间分配你的请求，以实现负载均衡，这样你就不会被锁定在单一供应商上。转录今天没有提供的是每次请求的路由控制。在 /api/v1/audio/transcriptions 上，你在聊天调用中设置的 order、only、allow_fallbacks、data_collection 和 sort 字段不会被应用。这个端点的 provider 块包含特定于提供商的选项：","该请求向 Groq 提供了专有名词的词汇提示，否则这些词会被错误处理。选项由提供商标识（slug）作为键，只有匹配的提供商的选项会被转发。如果你需要固定特定提供商或在转录上强制执行每次请求的数据策略，这个端点目前还不提供该控制功能。完整的提供商对象在提供商路由文档中有说明：https://openrouter.ai/docs/guides/routing/provider-selection。","OpenRouter 不标注提供商价格：https://openrouter.ai/pricing，所以目录价格就是你支付的价格，Zero Completion Insurance 意味着转录失败时不会收费。如果你已经有提供商协议，BYOK：https://openrouter.ai/docs/guides/overview/auth/byok 允许你通过你自己的提供商密钥进行路由，并只支付我们的平台费用，而不是按使用量的费用模式，对于按需付费模式每月前 100 万次请求还免收费用。","有四个约束条件决定了你如何构建一个转录调用：","因为超时限制是对处理时间而不是音频长度进行限制，所以单凭片段时长无法判断它是否能被处理。一个长时间的录音，比如通宵游戏，需要分块处理；单次调用无法覆盖它。","对于字幕，默认响应是文本加使用情况，不包含时间。设置 response_format 为 verbose_json，你将获得段级时间戳，如果你传入 timestamp_granularities: [\"word\"]，还会得到词级时间戳。这在 OpenAI 兼容提供商（OpenAI、Groq、Together）上有效；其他提供商会以 400 拒绝。没有内置的 .srt / .vtt 输出，因此字幕文件需要你自己根据时间戳生成。","您支付模型目录费率，我们不加收任何费用，usage.cost 字段会告诉您每次请求的确切费用。Whisper 类模型按音频秒数收费，新型号按 token 收费。","费率会变化，因此我们在每个模型目录页面上保持实时数据：https://openrouter.ai/models，而不是在这里打印。读取响应中的 usage.cost 可以告诉您每次请求实际花费多少。STT 模型是付费的，因此 API 转录会从您的信用余额中扣除费用。","要开始使用，请先在 Playground 中确认模型适合您的音频：https://openrouter.ai/playground，接入调用，并读取每次请求的 usage.cost，从第一天起就可以计量花费。","将 base64 编码的音频发送到 POST /api/v1/audio/transcriptions，并提供 model 和 input_audio 对象（包括 data 和 format）。响应是 JSON，包含 text 字符串（转录文本）和 usage 对象（秒数、tokens 和费用）。它使用与 Chat Completions 相同的 Bearer API Key 和认证。","是的。Whisper 类模型可用于转录，使用 openai/whisper-1 作为标识。STT 模型 ID 不在默认的 /api/v1/models 列表中，因此需要通过 ?output_modalities=transcription 进行过滤或浏览语音转文本合集来发现：https://openrouter.ai/collections/speech-to-text-models。Whisper 按音频时长收费，每秒计费；新 STT 模型按 token 收费。","常用格式包括 wav、mp3、flac、m4a、ogg、webm 和 aac，这些需要在 input_audio.format 字段中指定。不同模型和提供方对格式支持不同，并非每个模型都接受所有格式。wav 是最安全的默认格式，兼容性最广；压缩格式如 mp3 则传输体积小、速度快。","支持时间戳。将 response_format 设置为 verbose_json 可获取片段级时间戳，并添加 timestamp_granularities: [\"word\"] 获取按词级别的时间戳，存储在 words 数组中。这在兼容 OpenAI 的提供方（OpenAI、Groq、Together）上有效；其他提供方会返回 400 错误。暂不支持 SRT/VTT 输出，因此需根据时间戳自行生成字幕文件。","实际限制是大约 60 秒的上游处理超时，而不是固定的音频长度上限。短音频和中等长度音频可以一次返回。对于长录音，将音频分段，逐段转录，然后将文本拼接在一起。","您支付的是模型目录价格，不加任何溢价。Whisper 类模型按音频秒计价；较新的 STT 模型按 token 计价。每个响应中的 usage.cost 字段会报告该请求的准确美元费用。"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"OpenRouter 新增音频转写端点 POST /api/v1/audio/transcriptions。用户可沿用 Chat Completions 的 API key 与认证方式，提交 base64 编码音频，并在单次响应中获得转写文本及用量对象。","background":"材料称，常见语音转文字接入方式包括部署 Whisper 服务，或为转写增加第二套供应商 SDK。该端点将转写与聊天流量置于同一平台，并可对由多个供应商托管的模型自动进行负载均衡。","viewpoint":"Aioga 判断，这项更新的主要价值是减少独立转写服务的接入与维护环节，而非证明转写质量必然提高。模型选择仍需结合准确率要求、语言组合与预算，并参考当前模型定价。","implications":"值得关注的是，Whisper 类模型按音频时长计价，较新的语音转文字模型则按 token 计价；响应还会报告音频秒数、token 数和请求成本。这可能方便开发者比较不同模型的成本结构。","nextStep":"开发者可先通过输出模态筛选语音转文字模型及当前价格，再用包含 model 与 input_audio 的请求进行小规模验证。可选参数包括语言提示、temperature 和 provider 配置，结果可直接读取 text 字段。","evidenceRefs":["title","summary","articleBody","source"],"status":"published","aiGenerated":true,"autoApproved":true,"generatedBy":"aioga-editorial:gpt-5.6-sol","reviewedBy":"aioga-editorial-review:gpt-5.6-sol","generatedAt":"2026-07-22T22:51:15.801Z","sourceHash":"1a6838a19e8a8392","review":{"approved":true,"groundedness":96,"clarity":92,"duplicationRisk":12,"blockingIssues":[],"notes":["“Aioga 判断”明确标示为观点，且“减少独立转写服务的接入与维护环节”可由无需新 SDK 或独立服务的原文表述合理推导。","“这可能方便开发者比较不同模型的成本结构”属于措辞审慎的合理分析，没有冒充已证实效果。","nextStep 中“通过输出模态筛选”与原文一致；如需提升可操作性，可补充具体筛选接口或参数，但不影响事实准确性。"]},"validation":{"passed":true,"mode":"ai-auto","revisions":0,"checks":["schema","length","source-attribution","low-source-overlap","no-html","independent-ai-review"]}},"tags":["技巧观点","OpenRouter：Announcements（RSS）"],"translations":{"zh-CN":{"title":"OpenRouter 新增音频转写 API，支持 Whisper 与 token 计价 STT 模型","summary":"OpenRouter 推出 POST /api/v1/audio/transcriptions 端点，用户可使用同一 API key 将 base64 编码音频发送至该端点，返回 JSON 格式文本与用量对象。","category":"技巧观点","source":"openrouter.ai","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter 新增音频转写 API，支持 Whisper 与 token 计价 STT 模型 - Aioga AI资讯","description":"OpenRouter 推出 POST /api/v1/audio/transcriptions 端点，用户可使用同一 API key 将 base64 编码音频发送至该端点，返回 JSON 格式文本与用量对象。","url":"https://www.aioga.com/news/cmrvo24p604bvbihbk4aexnv6/"},"en":{"title":"OpenRouter adds an audio transcription API, supporting Whisper and token-priced STT models","summary":"OpenRouter launched the POST /api/v1/audio/transcriptions endpoint, allowing users to send base64-encoded audio to this endpoint using the same API key, and it returns a JSON-formatted text and usage object.","category":"Insights","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter adds an audio transcription API, supporting Whisper and token-priced STT models - Aioga AI News","description":"OpenRouter launched the POST /api/v1/audio/transcriptions endpoint, allowing users to send base64-encoded audio to this endpoint using the same API key, and it returns a JSON-forma...","url":"https://www.aioga.com/en/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:06:28.098Z"},"ja":{"title":"OpenRouter が音声転写 API を追加し、Whisper とトークン課金の STT モデルに対応","summary":"OpenRouter は POST /api/v1/audio/transcriptions エンドポイントを公開し、ユーザーは同じ API キーを使って base64 エンコードされた音声をこのエンドポイントに送信でき、JSON 形式のテキストと使用量オブジェクトを返します。","category":"ヒントと視点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter が音声転写 API を追加し、Whisper とトークン課金の STT モデルに対応 - Aioga AIニュース","description":"OpenRouter は POST /api/v1/audio/transcriptions エンドポイントを公開し、ユーザーは同じ API キーを使って base64 エンコードされた音声をこのエンドポイントに送信でき、JSON 形式のテキストと使用量オブジェクトを返します。","url":"https://www.aioga.com/ja/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:06:44.866Z"},"ko":{"title":"OpenRouter 새로운 오디오 전사 API 추가, Whisper 및 토큰 기반 요금 STT 모델 지원","summary":"OpenRouter는 POST /api/v1/audio/transcriptions 엔드포인트를 출시했으며, 사용자는 동일한 API 키를 사용하여 base64로 인코딩된 오디오를 해당 엔드포인트로 전송할 수 있고, JSON 형식의 텍스트 및 사용량 객체를 반환합니다.","category":"인사이트","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter 새로운 오디오 전사 API 추가, Whisper 및 토큰 기반 요금 STT 모델 지원 - Aioga AI 뉴스","description":"OpenRouter는 POST /api/v1/audio/transcriptions 엔드포인트를 출시했으며, 사용자는 동일한 API 키를 사용하여 base64로 인코딩된 오디오를 해당 엔드포인트로 전송할 수 있고, JSON 형식의 텍스트 및 사용량 객체를 반환합니다.","url":"https://www.aioga.com/ko/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:07:34.910Z"},"es":{"title":"OpenRouter ha añadido una API de transcripción de audio, compatible con Whisper y modelos STT con tarificación por token","summary":"OpenRouter ha lanzado el endpoint POST /api/v1/audio/transcriptions, donde los usuarios pueden enviar audio codificado en base64 a través de la misma clave API a este endpoint, devolviendo texto en formato JSON y un objeto de uso.","category":"Ideas","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter ha añadido una API de transcripción de audio, compatible con Whisper y modelos STT con tarificación por token - Aioga Noticias de IA","description":"OpenRouter ha lanzado el endpoint POST /api/v1/audio/transcriptions, donde los usuarios pueden enviar audio codificado en base64 a través de la misma clave API a este endpoint, dev...","url":"https://www.aioga.com/es/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:07:32.981Z"},"fr":{"title":"OpenRouter ajoute une API de transcription audio, prenant en charge les modèles STT Whisper et tarifés par token","summary":"OpenRouter a lancé le point de terminaison POST /api/v1/audio/transcriptions, permettant aux utilisateurs d'envoyer de l'audio encodé en base64 à ce point de terminaison avec la même clé API, et de recevoir du texte au format JSON ainsi qu'un objet de consommation.","category":"Analyses","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter ajoute une API de transcription audio, prenant en charge les modèles STT Whisper et tarifés par token - Aioga Actualités IA","description":"OpenRouter a lancé le point de terminaison POST /api/v1/audio/transcriptions, permettant aux utilisateurs d'envoyer de l'audio encodé en base64 à ce point de terminaison avec la mê...","url":"https://www.aioga.com/fr/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:08:17.475Z"},"de":{"title":"OpenRouter fügt eine Audio-Transkriptions-API hinzu, die Whisper und tokenbasiert abgerechnete STT-Modelle unterstützt","summary":"OpenRouter hat den Endpunkt POST /api/v1/audio/transcriptions eingeführt, über den Benutzer mit demselben API-Schlüssel base64-kodierte Audiodateien an diesen Endpunkt senden können, wobei als Antwort ein JSON-formatierter Text und ein Nutzungsobjekt zurückgegeben werden.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter fügt eine Audio-Transkriptions-API hinzu, die Whisper und tokenbasiert abgerechnete STT-Modelle unterstützt - Aioga KI-News","description":"OpenRouter hat den Endpunkt POST /api/v1/audio/transcriptions eingeführt, über den Benutzer mit demselben API-Schlüssel base64-kodierte Audiodateien an diesen Endpunkt senden könne...","url":"https://www.aioga.com/de/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:08:21.027Z"},"pt-BR":{"title":"OpenRouter adiciona API de transcrição de áudio, suportando Whisper e modelo STT com cobrança por token","summary":"OpenRouter lançou o endpoint POST /api/v1/audio/transcriptions, permitindo que os usuários enviem áudio codificado em base64 para esse endpoint usando a mesma chave de API, retornando texto em formato JSON e um objeto de uso.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter adiciona API de transcrição de áudio, suportando Whisper e modelo STT com cobrança por token - Aioga Notícias de IA","description":"OpenRouter lançou o endpoint POST /api/v1/audio/transcriptions, permitindo que os usuários enviem áudio codificado em base64 para esse endpoint usando a mesma chave de API, retorna...","url":"https://www.aioga.com/pt-BR/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:09:04.383Z"},"ru":{"title":"OpenRouter добавляет API преобразования аудио в текст, поддерживающий модели STT Whisper и с тарификацией по токенам","summary":"OpenRouter выпустил конечную точку POST /api/v1/audio/transcriptions, пользователи могут использовать один и тот же API ключ для отправки аудио в кодировке base64 на эту конечную точку, возвращается текст в формате JSON и объект использования.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter добавляет API преобразования аудио в текст, поддерживающий модели STT Whisper и с тарификацией по токенам - Aioga Новости ИИ","description":"OpenRouter выпустил конечную точку POST /api/v1/audio/transcriptions, пользователи могут использовать один и тот же API ключ для отправки аудио в кодировке base64 на эту конечную т...","url":"https://www.aioga.com/ru/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:09:07.226Z"},"ar":{"title":"OpenRouter أضاف واجهة برمجة تطبيقات تحويل الصوت إلى نص، يدعم نماذج STT الخاصة بـ Whisper وتسعير بالتوكن","summary":"أطلقت OpenRouter نقطة النهاية POST /api/v1/audio/transcriptions، حيث يمكن للمستخدمين استخدام نفس مفتاح API لإرسال الصوت المشفر بـ base64 إلى هذه النقطة، وسيتم إرجاع نص بصيغة JSON مع كائن الاستخدام.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter أضاف واجهة برمجة تطبيقات تحويل الصوت إلى نص، يدعم نماذج STT الخاصة بـ Whisper وتسعير بالتوكن - Aioga أخبار الذكاء الاصطناعي","description":"أطلقت OpenRouter نقطة النهاية POST /api/v1/audio/transcriptions، حيث يمكن للمستخدمين استخدام نفس مفتاح API لإرسال الصوت المشفر بـ base64 إلى هذه النقطة، وسيتم إرجاع نص بصيغة JSON م...","url":"https://www.aioga.com/ar/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:09:53.064Z"},"hi":{"title":"OpenRouter ने ऑडियो ट्रांस्क्रिप्शन API जोड़ा, Whisper और टोकन आधारित STT मॉडल को सपोर्ट करता है","summary":"OpenRouter ने POST /api/v1/audio/transcriptions एंडपॉइंट पेश किया है, उपयोगकर्ता उसी API कुंजी का उपयोग करके base64 एनकोड किए गए ऑडियो को इस एंडपॉइंट पर भेज सकते हैं, और JSON प्रारूप में टेक्स्ट और उपयोग वस्तु प्राप्त कर सकते हैं।","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter ने ऑडियो ट्रांस्क्रिप्शन API जोड़ा, Whisper और टोकन आधारित STT मॉडल को सपोर्ट करता है - Aioga AI समाचार","description":"OpenRouter ने POST /api/v1/audio/transcriptions एंडपॉइंट पेश किया है, उपयोगकर्ता उसी API कुंजी का उपयोग करके base64 एनकोड किए गए ऑडियो को इस एंडपॉइंट पर भेज सकते हैं, और JSON प्रार...","url":"https://www.aioga.com/hi/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:09:56.953Z"},"it":{"title":"OpenRouter ha aggiunto una nuova API di trascrizione audio, che supporta i modelli STT Whisper e basati su token","summary":"OpenRouter ha lanciato l'endpoint POST /api/v1/audio/transcriptions, gli utenti possono utilizzare la stessa chiave API per inviare audio codificato in base64 a questo endpoint, restituendo testo in formato JSON e oggetti di utilizzo.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter ha aggiunto una nuova API di trascrizione audio, che supporta i modelli STT Whisper e basati su token - Aioga Notizie IA","description":"OpenRouter ha lanciato l'endpoint POST /api/v1/audio/transcriptions, gli utenti possono utilizzare la stessa chiave API per inviare audio codificato in base64 a questo endpoint, re...","url":"https://www.aioga.com/it/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:10:48.784Z"},"nl":{"title":"OpenRouter heeft een nieuwe audio-transcriptie API toegevoegd, die Whisper en token-geprijsde STT-modellen ondersteunt","summary":"OpenRouter heeft het endpoint POST /api/v1/audio/transcriptions geïntroduceerd, waarmee gebruikers dezelfde API-sleutel kunnen gebruiken om base64-gecodeerde audio naar dat endpoint te sturen, en het retourneert een JSON-formaat tekst en gebruiksobject.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter heeft een nieuwe audio-transcriptie API toegevoegd, die Whisper en token-geprijsde STT-modellen ondersteunt - Aioga AI-nieuws","description":"OpenRouter heeft het endpoint POST /api/v1/audio/transcriptions geïntroduceerd, waarmee gebruikers dezelfde API-sleutel kunnen gebruiken om base64-gecodeerde audio naar dat endpoin...","url":"https://www.aioga.com/nl/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:10:40.648Z"},"tr":{"title":"OpenRouter yeni ses transkripsiyon API'si ekledi, Whisper ve token tabanlı STT modeli destekliyor","summary":"OpenRouter, POST /api/v1/audio/transcriptions uç noktasını başlattı; kullanıcılar aynı API anahtarını kullanarak base64 kodlu sesleri bu uç noktaya gönderebilir ve JSON formatında metin ile kullanım nesnesi alabilir.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter yeni ses transkripsiyon API'si ekledi, Whisper ve token tabanlı STT modeli destekliyor - Aioga AI Haberleri","description":"OpenRouter, POST /api/v1/audio/transcriptions uç noktasını başlattı; kullanıcılar aynı API anahtarını kullanarak base64 kodlu sesleri bu uç noktaya gönderebilir ve JSON formatında...","url":"https://www.aioga.com/tr/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:11:29.694Z"},"vi":{"title":"OpenRouter thêm API chuyển giọng nói thành văn bản, hỗ trợ mô hình STT Whisper và tính giá theo token","summary":"OpenRouter ra mắt endpoint POST /api/v1/audio/transcriptions, người dùng có thể sử dụng cùng một API key để gửi âm thanh mã hóa base64 tới endpoint này, trả về văn bản định dạng JSON và đối tượng sử dụng.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter thêm API chuyển giọng nói thành văn bản, hỗ trợ mô hình STT Whisper và tính giá theo token - Tin tức AI Aioga","description":"OpenRouter ra mắt endpoint POST /api/v1/audio/transcriptions, người dùng có thể sử dụng cùng một API key để gửi âm thanh mã hóa base64 tới endpoint này, trả về văn bản định dạng JS...","url":"https://www.aioga.com/vi/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:11:34.831Z"},"id":{"title":"OpenRouter menambahkan API transkripsi audio, mendukung model STT Whisper dan penetapan harga token","summary":"OpenRouter meluncurkan endpoint POST /api/v1/audio/transcriptions, pengguna dapat menggunakan API key yang sama untuk mengirim audio yang dikodekan dalam base64 ke endpoint tersebut, dan mengembalikan teks dalam format JSON serta objek penggunaan.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter menambahkan API transkripsi audio, mendukung model STT Whisper dan penetapan harga token - Berita AI Aioga","description":"OpenRouter meluncurkan endpoint POST /api/v1/audio/transcriptions, pengguna dapat menggunakan API key yang sama untuk mengirim audio yang dikodekan dalam base64 ke endpoint tersebu...","url":"https://www.aioga.com/id/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:12:15.287Z"},"th":{"title":"OpenRouter เพิ่ม API การถอดเสียงจากเสียง รองรับโมเดล STT แบบ Whisper และคิดค่าใช้จ่ายตามโทเคน","summary":"OpenRouter เปิดตัว endpoint POST /api/v1/audio/transcriptions ผู้ใช้สามารถใช้ API key เดียวกันส่งเสียงที่เข้ารหัสเป็น base64 ไปยัง endpoint นี้ และจะได้รับข้อความในรูปแบบ JSON พร้อมวัตถุการใช้งาน","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter เพิ่ม API การถอดเสียงจากเสียง รองรับโมเดล STT แบบ Whisper และคิดค่าใช้จ่ายตามโทเคน - ข่าว AI Aioga","description":"OpenRouter เปิดตัว endpoint POST /api/v1/audio/transcriptions ผู้ใช้สามารถใช้ API key เดียวกันส่งเสียงที่เข้ารหัสเป็น base64 ไปยัง endpoint นี้ และจะได้รับข้อความในรูปแบบ JSON พร้อ...","url":"https://www.aioga.com/th/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:12:24.597Z"},"pl":{"title":"OpenRouter wprowadza nowe API do transkrypcji audio, obsługujące modele STT Whisper i rozliczanie według tokenów","summary":"OpenRouter wprowadza punkt końcowy POST /api/v1/audio/transcriptions, użytkownicy mogą używać tego samego klucza API, aby wysyłać zakodowany w base64 dźwięk do tego punktu końcowego, a w odpowiedzi otrzymują tekst w formacie JSON oraz obiekt zużycia.","category":"技巧观点","source":"OpenRouter：Announcements（RSS）","aggregationSource":"OpenRouter：Announcements（RSS）","pageTitle":"OpenRouter wprowadza nowe API do transkrypcji audio, obsługujące modele STT Whisper i rozliczanie według tokenów - Aioga Wiadomości AI","description":"OpenRouter wprowadza punkt końcowy POST /api/v1/audio/transcriptions, użytkownicy mogą używać tego samego klucza API, aby wysyłać zakodowany w base64 dźwięk do tego punktu końcoweg...","url":"https://www.aioga.com/pl/news/cmrvo24p604bvbihbk4aexnv6/","contentTranslated":true,"sourceHash":"7598c80a8f91d8a5","translatedAt":"2026-07-22T17:13:13.092Z"}}}}