# Speech-to-Text and Text-to-Speech with Asterisk

**URL:** <https://community.asterisk.org/t/speech-to-text-and-text-to-speech-with-asterisk/101335>\
**Category:** Asterisk APIs\
**Created:** [March 5, 2024, 10:23am UTC](https://community.asterisk.org/t/speech-to-text-and-text-to-speech-with-asterisk/101335 "2024-03-05T10:23:51Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![rogerfederer](https://avatars.discourse-cdn.com/v4/letter/r/a587f6/32.png) [@rogerfederer](https://community.asterisk.org/u/rogerfederer)\
**Post date:** [March 5, 2024, 10:23am UTC](https://community.asterisk.org/t/speech-to-text-and-text-to-speech-with-asterisk/101335/1 "2024-03-05T10:23:51Z")

</div>

Hello! I’m in the process of developing a stasis app and I need to integrate Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) functionalities into my application. My questions are: When using the AEAP protocol, is there an option to utilize a speech provider other than Google? If not, how can I implement an alternative provider? Additionally, since AEAP only supports ASR, how can I incorporate the TTS functionality into my application?

Thank you!

---

<div class="post-metadata">

**Author:** ![jcolp](https://sea1.discourse-cdn.com/asterisk/user_avatar/community.asterisk.org/jcolp/32/8848_2.png) [@jcolp](https://community.asterisk.org/u/jcolp)\
**Post date:** [March 5, 2024, 10:30am UTC](https://community.asterisk.org/t/speech-to-text-and-text-to-speech-with-asterisk/101335/2 "2024-03-05T10:30:28Z")

</div>

The project provides a SAMPLE implementation that uses Google for AEAP. It’s up to you to turn that into something to use for production, including with another provider if you want. AEAP is just an interface between the dialplan speech support and an outside application.

There is no built in included TTS functionality.

For ARI people are commonly using the external media support instead, which sends/receives audio to the ARI application where it can be used for any purpose - such as ASR, TTS, or even offloading recording in realtime.

---

<div class="post-metadata">

**Author:** ![rogerfederer](https://avatars.discourse-cdn.com/v4/letter/r/a587f6/32.png) [@rogerfederer](https://community.asterisk.org/u/rogerfederer)\
**Post date:** [March 18, 2024, 3:51pm UTC](https://community.asterisk.org/t/speech-to-text-and-text-to-speech-with-asterisk/101335/3 "2024-03-18T15:51:55Z")

</div>

Thank you in advance for the feedback! I’m strongly considering using AEAP for my ASR/TTS project. I’ve been searching for answers to some questions that I have, but unfortunately, I haven’t had much success. I’d like to inquire if AEAP includes any speech start or end recognition and if it supports SSL Proxy usage.

Thanks again!

---

<div class="post-metadata">

**Author:** ![jcolp](https://sea1.discourse-cdn.com/asterisk/user_avatar/community.asterisk.org/jcolp/32/8848_2.png) [@jcolp](https://community.asterisk.org/u/jcolp)\
**Post date:** [March 18, 2024, 3:53pm UTC](https://community.asterisk.org/t/speech-to-text-and-text-to-speech-with-asterisk/101335/4 "2024-03-18T15:53:38Z")

</div>

It has no speech start or end recognition. I believe there’s an open feature request for SSL support.

---

<div class="post-metadata">

**Author:** ![system](https://global.discourse-cdn.com/asterisk/original/2X/4/475d0c889911cfb84ac4881ad6df8b523e3f9105.png) [@system](https://community.asterisk.org/u/system)\
**Post date:** [April 17, 2024, 3:54pm UTC](https://community.asterisk.org/t/speech-to-text-and-text-to-speech-with-asterisk/101335/5 "2024-04-17T15:54:33Z")

</div>

Closed on April 17, 2024, 3:54pm UTC

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.