借助 Gemini 3.5 Transcribe 实现智能转录
英文标题：Intelligent transcription with Gemini 3.5 Transcribe
Google 推出 Gemini 3.5 Transcribe，称其为目前最精准的语音转文字模型，能够将原始音频直接转换为准确、润色且格式化的文本。该模型可处理背景噪声、复杂术语、口语停顿和自我修正，并支持自定义词汇、85 种以上语言及多说话人识别。开发者现可通过 Gemini API 中的 Live API 和 Interactions API，分别构建低延迟实时语音应用与录音转录、通话分析等工作流。根据 Artificial Analysis 的测量结果，该模型在流式和非流式场景中的平均词错误率分别为 4.0% 和 2.6%。
9.8 KB
中文
今天，我们推出 Gemini 3.5 Transcribe——这是我们迄今最精准的语音转文字模型，专为智能语音交互设计。不同于难以应对背景噪声、复杂术语和口语不流畅内容清理的传统语音识别模型，Gemini 3.5 Transcribe 可将原始音频直接转换为准确、润色且格式化的文本。
在 Gemini app 和 Android 等产品中，我们已经看到消费者借助这一转录模型及新的语音能力获益，例如 Android 上的 Rambler 和 macOS 版 Gemini app。现在，开发者也可通过 Google AI Studio 中的 Gemini API 和 Gemini Enterprise Agent Platform 使用 Gemini 3.5 Transcribe 构建类似能力。
我们打造 3.5 Transcribe，旨在无缝接入开发者工作流，无论你是在构建语音 Agent、实时字幕工具，还是通话后分析流水线。该模型可通过两个独立的 API 使用：
- 实时流式处理： 通过 Live API，使用
gemini-3.5-transcribe-live提供持续的双向流式传输和亚秒级延迟，适用于交互式语音应用。 - 预录音频处理： 通过 Interactions API，使用
gemini-3.5-transcribe转录录制音频、会议、通话记录等内容，并提供说话人归属和词级时间戳。
获得更精准、更智能的转录
Gemini 3.5 Transcribe 旨在捕捉你的自然说话方式，更好地理解你的意图并识别自定义词汇，从而让你能够通过语音执行任务。
- 智能转录： 可无缝处理自我修正（例如 “我们周二见——不，周三”），删除填充词（“嗯”和“啊”），并自动格式化文本。
- 函数调用： 该模型可通过函数调用，将图像生成和文件分析等复杂任务委派给其他 Gemini 模型。目前已在 macOS 版 Gemini app 中提供。
- 更精准的转录： 根据 Artificial Analysis 的测量结果，在流式场景中的平均词错误率（WER）达到 4.0%，在非流式场景中达到 2.6%。该模型在嘈杂的真实环境中表现强劲，能够准确识别邮政编码、订单 ID 等字母数字实体。
- 自定义词汇： 可通过无缝适应所提供的自定义词汇，识别专业术语和独特拼写。
- 全球语言支持： 可自动检测并转录超过 85 种语言，并无缝处理地区口音和多样方言。
- 多说话人识别： 可在预录音频中准确标注最多三位说话人的发言及其时间戳（对 3 位以上说话人的支持仍处于实验阶段）。
English / 原文
Today, we’re introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions. Unlike conventional speech recognition models that struggle with background noise, complex jargon, and disfluency cleanup, Gemini 3.5 Transcribe converts raw audio directly into accurate, polished, formatted text.
Across our products like the Gemini app and on Android, we’ve seen consumers already benefiting from this transcription model with new voice capabilities like Rambler on Android and in the Gemini app on macOS. Now, developers can build similar capabilities with Gemini 3.5 Transcribe in the Gemini API in Google AI Studio and Gemini Enterprise Agent Platform.
We've built 3.5 Transcribe to plug seamlessly into your developer workflows, whether you’re building voice agents, real-time captioning tools, or post-call analytics pipelines. The model is available across two separate APIs:
- Real-time streaming: Delivers continuous, bidirectional streaming with sub-second latency for interactive voice apps via the Live API using
gemini-3.5-transcribe-live****. - Pre-recorded audio processing: Transcribes recorded audio, meetings, call logs, and more with speaker attribution and word-level timestamps via the Interactions API using
gemini-3.5-transcribe****.
Get more precise and intelligent transcription
Gemini 3.5 Transcribe is designed to capture your natural speaking style to better understand your intent and recognize custom vocabulary, so you can execute tasks with your voice.
- Smart transcription: Seamlessly handles self-corrections (like "let’s meet Tuesday—no, Wednesday"), removes filler words (“ums” and ‘“ahs"), auto-formats your text.
- Function calling: The model can delegate complex tasks (such as image generation and file analysis) to other Gemini models via function calls. Currently available in the Gemini macOS app.
- More precise transcription: As measured by Artificial Analysis, achieves an average Word Error Rate (WER) of 4.0% for streaming and 2.6% for non-streaming use-cases. It shows strong performance across noisy, real-world environments, accurately capturing alphanumeric entities like postal codes and order IDs.
- Custom vocabulary: Recognizes specialized jargon and unique spellings by seamlessly adapting transcriptions to your provided custom vocabulary.
- Global language support: Automatically detects and transcribes over 85 languages, seamlessly handling regional accents and diverse dialects.
- Multi-speaker identification: Accurately attributes speech in pre-recorded audio with timestamps for up to three speakers (support for 3+ speakers is experimental).