@jcode.labs/mimir-tts 0.4.2 → 0.4.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +25 -34
- package/package.json +2 -2
package/README.md
CHANGED
|
@@ -1,53 +1,44 @@
|
|
|
1
|
-
# Mimir TTS
|
|
1
|
+
# Mimir TTS Package
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
`@jcode.labs/mimir-tts` is the standalone text-to-speech package used by Mimir audio summaries.
|
|
4
|
+
It gives Mimir a plug-and-play narration renderer without making audio generation part of the core
|
|
5
|
+
RAG pipeline.
|
|
4
6
|
|
|
5
|
-
|
|
7
|
+
**Full documentation:** https://github.com/jcode-works/jcode-mimir#readme
|
|
6
8
|
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
- Edge MP3 for the same quality path as the global Voice Forge skill. It uses the external
|
|
10
|
-
`edge-tts` CLI, `fr-FR-DeniseNeural`, and `+0%` rate, and must be requested explicitly.
|
|
9
|
+
This npm README is intentionally short because package READMEs are displayed separately on npm. The
|
|
10
|
+
GitHub root README is the canonical product documentation.
|
|
11
11
|
|
|
12
|
-
|
|
13
|
-
for private content.
|
|
12
|
+
## What It Does
|
|
14
13
|
|
|
15
|
-
|
|
14
|
+
The package renders text files into local audio files for briefings, study notes, project summaries,
|
|
15
|
+
or agent-generated narration.
|
|
16
16
|
|
|
17
|
-
|
|
18
|
-
pnpm add -D @jcode.labs/mimir-tts
|
|
19
|
-
```
|
|
17
|
+
It supports two explicit paths:
|
|
20
18
|
|
|
21
|
-
|
|
22
|
-
|
|
23
|
-
```bash
|
|
24
|
-
pipx install edge-tts
|
|
25
|
-
```
|
|
19
|
+
- Transformers.js WAV for offline or confidential content. This is the default path.
|
|
20
|
+
- Edge TTS MP3 for higher-quality online narration when sending the text to Edge TTS is acceptable.
|
|
26
21
|
|
|
27
|
-
|
|
22
|
+
It does not require Python, ffmpeg, Piper, XTTS, or a local model server for the default
|
|
23
|
+
Transformers.js path.
|
|
28
24
|
|
|
29
|
-
|
|
25
|
+
## Install
|
|
30
26
|
|
|
31
27
|
```bash
|
|
32
|
-
pnpm
|
|
33
|
-
--engine edge \
|
|
34
|
-
--out .mimir/audio/tax-summary.mp3
|
|
28
|
+
pnpm add -D @jcode.labs/mimir-tts
|
|
35
29
|
```
|
|
36
30
|
|
|
37
|
-
|
|
31
|
+
## Quick Start
|
|
38
32
|
|
|
39
33
|
```bash
|
|
40
|
-
pnpm exec mimir-tts
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
--out .mimir/audio/summary.wav
|
|
34
|
+
pnpm exec mimir-tts doctor --json
|
|
35
|
+
pnpm exec mimir-tts render /tmp/summary.txt --offline --out .mimir/audio/summary.wav
|
|
36
|
+
pnpm exec mimir-tts render /tmp/summary.txt --engine edge --out .mimir/audio/summary.mp3
|
|
44
37
|
```
|
|
45
38
|
|
|
46
|
-
|
|
39
|
+
The default engine is `transformers` for offline/confidential WAV output. Use `--engine edge` only
|
|
40
|
+
when sending narration text to online Edge TTS is acceptable.
|
|
47
41
|
|
|
48
|
-
|
|
49
|
-
pnpm exec mimir-tts doctor --json
|
|
50
|
-
```
|
|
42
|
+
## License
|
|
51
43
|
|
|
52
|
-
|
|
53
|
-
Override it with `--model` or `MIMIR_TTS_MODEL`.
|
|
44
|
+
MIT (c) Jean-Baptiste Thery.
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@jcode.labs/mimir-tts",
|
|
3
|
-
"version": "0.4.
|
|
3
|
+
"version": "0.4.4",
|
|
4
4
|
"description": "Plug-and-play Edge-quality and offline text-to-speech for Mimir audio summaries.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"license": "MIT",
|
|
@@ -24,7 +24,7 @@
|
|
|
24
24
|
"url": "git+https://github.com/jcode-works/jcode-mimir.git",
|
|
25
25
|
"directory": "packages/mimir-tts"
|
|
26
26
|
},
|
|
27
|
-
"homepage": "https://github.com/jcode-works/jcode-mimir
|
|
27
|
+
"homepage": "https://github.com/jcode-works/jcode-mimir#readme",
|
|
28
28
|
"bugs": {
|
|
29
29
|
"url": "https://github.com/jcode-works/jcode-mimir/issues"
|
|
30
30
|
},
|