---
title: "Generate Audio for Transcripts"
method: POST
path: "/v2/process-log/generate-audio"
tags: ["Process Logs"]
---

# Generate Audio for Transcripts

`POST /v2/process-log/generate-audio`

## Request

- Base URL: `https://api.translate.video` (the document declares no server; this is the origin it was published from)
- URL: `https://api.translate.video/v2/process-log/generate-audio`
- Auth: HTTP bearer

## Headers

- `vitra-apitoken` string

## Request body

- SpeechGenerationDto
  - `processId` string, required: Process id
  - `targetLanguage` string, required: Target Languge
  - `subtitles` boolean: Subtitles to generate
  - `voice` object: Voice to use when diarization is disabled
  - `voices` object: Speaker -> voice map used when diarization is enabled
  - `diarization` boolean: Enable diarization; when true, `voices` is required; when false, `voice` is required. Can be skipped when adding subtitles.
  - `sourceLanguage` string, required: Source Language
  - `projectId` string, required: Project id
  - `generateForAllTranscripts` boolean, required: Generate speech for all cards (true) or only for transcripts missing audio (false)
  - `optimize` boolean, required: Enable rate optimization for audio-video sync. When disabled, video plays at 1x speed.

## Response `201`

Success

---

[API](https://skmtc.dev/translate/apis/translate-video-server.md) - [All operations](https://skmtc.dev/translate/apis/translate-video-server/llms.txt) - [OpenAPI document](https://skmtc.dev/translate/apis/translate-video-server/revisions/d99673eed87e?raw)