ben.carrasco/speech-utils
1
0
Fork 0
mirror of https://github.com/jambonz/speech-utils.git synced 2025-12-19 03:37:49 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into feat/azure_tts

Browse Source
This commit is contained in:
Hoan Luu Huu
2024-03-30 17:04:01 +07:00
committed by GitHub
parent f06f96a6f0 8f3e930004
commit 16dd7a2805
4 changed files with 56 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
lib/synth-audio.js
View File

@@ -635,6 +635,8 @@ const synthElevenlabs = async(logger, {
if (!process.env.JAMBONES_DISABLE_TTS_STREAMING && !renderForCaching && !disableTtsStreaming) {
let params = '';
params += `{api_key=${api_key}`;
params += ',vendor=elevenlabs';
params += `,voice=${voice}`;
params += `,model_id=${model_id}`;
params += `,optimize_streaming_latency=${opts.optimize_streaming_latency || 2}`;
params += ',write_cache_file=1';
@@ -683,6 +685,7 @@ const synthWhisper = async(logger, {credentials, stats, voice, text, renderForCa
let params = '';
params += `{api_key=${api_key}`;
params += `,model_id=${model_id}`;
params += ',vendor=whisper';
params += `,voice=${voice}`;
params += ',write_cache_file=1';
if (speed) params += `,speed=${speed}`;

4
package-lock.json generated
View File

@@ -1,12 +1,12 @@
{
"name": "@jambonz/speech-utils",
"version": "0.0.42",
"version": "0.0.44",
"lockfileVersion": 2,
"requires": true,
"packages": {
"": {
"name": "@jambonz/speech-utils",
"version": "0.0.42",
"version": "0.0.44",
"license": "MIT",
"dependencies": {
"@aws-sdk/client-polly": "^3.496.0",

2
package.json
View File

@@ -1,6 +1,6 @@
{
"name": "@jambonz/speech-utils",
"version": "0.0.42",
"version": "0.0.44",
"description": "TTS-related speech utilities for jambonz",
"main": "index.js",
"author": "Dave Horton",

50
test/synth.js
View File

@@ -214,6 +214,56 @@ test('Azure speech synth tests', async(t) => {
client.quit();
});
test('Azure SSML tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);
if (!process.env.MICROSOFT_API_KEY || !process.env.MICROSOFT_REGION) {
t.pass('skipping Microsoft speech synth tests since MICROSOFT_API_KEY or MICROSOFT_REGION not provided');
return t.end();
}
try {
const text = `<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xmlns:mstts="https://www.w3.org/2001/mstts" xml:lang="en-US">
<voice name="en-US-JennyMultilingualNeural">
<mstts:express-as style="cheerful" styledegree="2">That'd be just amazing!
</mstts:express-as>
</voice>
</speak>`;
let opts = await synthAudio(stats, {
vendor: 'microsoft',
credentials: {
api_key: process.env.MICROSOFT_API_KEY,
region: process.env.MICROSOFT_REGION,
},
language: 'en-US',
voice: 'en-US-ChristopherNeural',
text,
});
t.ok(!opts.servedFromCache, `successfully synthesized microsoft audio to ${opts.filePath}`);
if (process.env.JAMBONES_HTTP_PROXY_IP && process.env.JAMBONES_HTTP_PROXY_PORT) {
t.pass('successfully used proxy to reach microsoft tts service');
}
opts = await synthAudio(stats, {
vendor: 'microsoft',
credentials: {
api_key: process.env.MICROSOFT_API_KEY,
region: process.env.MICROSOFT_REGION,
},
language: 'en-US',
voice: 'en-US-ChristopherNeural',
text,
});
t.ok(opts.servedFromCache, `successfully retrieved microsoft audio from cache ${opts.filePath}`);
} catch (err) {
console.error(err);
t.end(err);
}
client.quit();
});
test('Azure custom voice speech synth tests', async(t) => {
const fn = require('..');
const {synthAudio, client} = fn(opts, logger);