Skip to content

feat: add Text to Speech endpoints with timestamp alignment and documentation #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
twangodev wants to merge 3 commits into
base: main
Choose a base branch
from
Open

feat: add Text to Speech endpoints with timestamp alignment and documentation #36

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fec9901
fix: improve docs for openapi.json, expose new params for tts
twangodev Dec 5, 2025
4f35a1d
fix: update descriptions and defaults in openapi.json for speech para…
twangodev Dec 10, 2025
e04eb6b
feat: add Text to Speech endpoints with timestamp alignment and docum…
twangodev Dec 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
49 changes: 49 additions & 0 deletions api-reference/endpoint/openapi-v1/tts-with-timestamp.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,49 @@
---
openapi: post /v1/tts/with_timestamp
title: 'Text to Speech with Timestamp'
description: 'Generate speech with word-level timestamp alignment'
icon: "clock"
iconType: "solid"
---

<Note>
This endpoint generates complete audio first, then aligns it with the input text to provide precise timing information for each segment. The response includes both the audio and an array of timestamp segments.
</Note>

## Response Format

The response is a JSON object containing:

| Field | Type | Description |
|-------|------|-------------|
| `audio_base64` | string | Base64-encoded audio data |
| `text` | string | The synthesized text (with emotion markers removed) |
| `alignment` | array | Array of timestamp segments |

Each timestamp segment contains:

| Field | Type | Description |
|-------|------|-------------|
| `text` | string | The text content of this segment |
| `start` | number | Start time in seconds |
| `end` | number | End time in seconds |

## Example Response

```json
{
"audio_base64": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8...",
"text": "Hello, world!",
"alignment": [
{"text": "Hello,", "start": 0.0, "end": 0.45},
{"text": "world!", "start": 0.52, "end": 1.1}
]
}
```

## Use Cases

- **Subtitle generation**: Automatically create synchronized subtitles for video content
- **Karaoke-style highlighting**: Highlight words as they are spoken
- **Accessibility features**: Provide visual indicators synchronized with audio playback
- **Audio editing**: Precisely locate and edit specific words in generated speech
Loading