Introduction
Choose the right HUMAIN Voice workflow, then follow the shortest path to a production-ready integration.
HUMAIN Voice turns complete recordings or live audio into text and generates speech from text. Start here to choose one workflow; the Quickstart owns installation and first-request instructions.
Choose by audio and outcome
| What you have or need | Use | Start here |
|---|---|---|
| A meeting, podcast, or other complete long recording | Batch transcription uploads the file and polls for a terminal result. | Quickstart |
| A complete audio unit that needs a latency-sensitive result, such as one agentic conversational turn | Fast transcription sends the full audio over Socket.IO. It is not live microphone streaming and is not the path for long recordings or podcasts. | SDK guide |
| Audio still being produced by a microphone, call, or media pipeline | Realtime transcription streams PCM16 and returns provisional and final results. | Quickstart |
| Text that must become playable speech | Text-to-speech returns PCM16; the recipe writes the WAV container. | TTS-to-WAV recipe |
| A runtime without a released SDK, or wire-level control | Direct API uses REST, HTTP streaming, or Socket.IO from a trusted backend. | API Guides |
If the audio already exists and you are unsure, choose batch. Choose realtime only when results must arrive while audio is still being produced.
Before you start
- These docs target JavaScript and Python SDK
0.18.0. - Obtain
API_KEYthrough your organization's access flow. This site renders theAPI_URLconfigured for its environment. - Socket.IO clients default to
/socket.io; passAPI_PATHonly when a deployment uses an override. The legacysautech.humain.comendpoint requires/realtime/socket.io. Keep the API key in a trusted server environment.
The Quickstart covers pinned installation, audio preparation, environment variables, and the first tested batch and realtime requests.
From first request to production
- Complete the Quickstart for batch or realtime.
- Use the language-specific SDK guide, or use API Guides for a direct integration.
- Add speaker labels, subtitles, or playable TTS output from Recipes.
- Handle structured errors, deadlines, and bounded retries with Errors and Rate Limits.
Make a first request
Install SDK 0.18.0 and complete a tested batch or realtime workflow.
Choose an SDK client
Review every released client, option, timeout, response, and lifecycle rule.
Inspect API contracts
Use validated HTTP schemas and generated operation documentation.
Machine-readable access
/llms.txtlists documentation entry points;/llms-full.txtcontains the complete Markdown bundle.- Narrative Markdown uses
/en/md/<slug>, for example/en/md/quickstart. - Generated API-reference Markdown uses
/en/api-reference/md/<slug>.