High quality, emotional, fluent and variable Text-to-Speech engine?

Question

After looking at some of services/tools, I've come to a conclusion. Most Text-to-Speech tools have too techy, robotic - in other words, bad quality c voices.

And yeah, on top of that, it looks like they come with a "hard-coded" voice templates, therefore shortening the variety/customization. Some tools allow you to set the reading speed and pitch', but that's not enough.

My guess about the problem behind the emotional aspect - it's hard to judge emotions from plain text, even more if it's just a sentence or two. Plus, the good ol' PC is a machine - machines don't have emotions, but that's a different story.

The thing that bothers me the most, is, quality. For example, there are these tools out there, that use to cut off apex of words, resulting in these techy voices. Feels like there's a problem with sentence construction or something. And yes, while people are working on such tools, I wonder, what keeps them from working a little more to improve those... cutting off the apex, that's not a small deal! Plus, have to keep in mind, that a good, quality Text-to-Speech software is worth, well... A LOT! Therefore resulting in a pretty profitable product.

Oh, under fluency I'm hiding questions, exclamations and so on. (Possible that those do not apply to fluency, but I'm not native English, please excuse me if that's the case.)

A list of tools I've looked into:

Quite impressive, but still have space for improvements (++)

<sup>- Loquendo : lacks voice variety, got some minor apex/fluency problems (depends on sentence), too much coughing and excuses in examples!
- Nuance Vocalizer : while still lacks variety, some of the provided voices are worthy.</sup>

---

Could as well cooperate to get more resources then to work on different, but almost equal products (--)

<sup>- eSpeak : one of the best robots out there, hence the program logo(?!)
- Natural Reader (dumb autoplay!!) : well, it got some fluency, but still that techy feeling kicks in.
- iSpeech : good laugh when setting the voice to Japanese with English text. I bet Japanese guys aren't very happy about it.
- Cepstral + Enhanced Voices ... plus the enhanced voices give the good ol' crappy result, so, except ~5 more voices, nothing have been enhanced.
- AT&T : decent fluency, but got problems with sentence endings and too much robo!
- LumenVox TTS : looks like coming from a background with lots of speech tools, but still results in robotic voices.
- And some more...</sup>

---

In case I've missed something worth a look, please share. Can be free, commercial, super expensive... as long as it works, I'm interested!

And the question(-s)..

1. What do you think are the main issues behind quality, fluency and variety of those voices? Since emotional aspect is hard to judge, I don't mind if you skip it, but if you have an idea or two, I wouldn't mind if you shared your thoughts
2. How is text transformed into speech? Like, what algorithms are used behind these tools? Maybe a fresh theory or two could come in handy.
3. Are those actually different engines/drivers or just different voice patterns for the same driver/engine?
4. Is it just me, or the quality between one of the first Text2Speech tools hasn't changed much (or at all) over the years? And have to admit, that this oldschool Apple's tool provides better results than some of the year 2000+ tools, at least when comparing video with what I've looked into.)

Stuppy

In my opinion, #2 and #3 above would make a couple of reasonable questions. The rest of it seems to invite discussion that's a bit beyond the scope of a Q&A forum. – Pattani

Huh, maybe somebody will be in the mood to answer some of these questions in this post, but yeah, I've started a new thread for question #2. – Stuppy

What do you mean by 'apex'? I've read some about speech synthesis and understanding, but I'm not familiar with this term in this context. I struck out with a Google search too. Maybe insert a definition? – Chrissie

Answer 1

I don't know if you're looking for an open solution, but if you have a Mac, you should check out OS X advanced speech markup and the "Repeat After Me" phrase building tool. It's really powerful. The Alex voice built into Mac OS X 10.5 and later is more advanced than the other voices.

On a Mac, highlight the following text, control-click, and go to Speech > Start Speaking:

You talkin' to me
[[inpt PHON]] [[slnc 500]] [[rate -30]]
+yUW _1tAOl=kIHn ~AX [[pbas +3]]+mIY?

http://www.mattmontag.com/personal/mac-os-x-speech-synthesis-markup

Takamatsu

And the 2nd/3rd line are some kind of options that make the voice feel more real? – Stuppy

Yes, well, it adds some fine tuning for emphasis and stuff. It sounds a lot better to my ear. You can also draw a breath with the @ symbol. – Takamatsu

Answer 2

The TTS used by Google Translate is quite good for short phrases, though likely to produce an unnatural intonation contour for anything complicated. Still, at the word level, it's impressive. There is a small code example here

And there's Ivona - They might make a slightly more articulation errors than e.g. Google Translate, but they do somewhat better on rhythm and intonation. Check out their 'Raveena' voice, it's one of their best yet.

Chrissie

Answer 3

I know that this is an old question, but I just saw the demo of "Watson" from IBM, it's pretty impressive!! They have support for several languages, you can control tone, pauses, intonation and some other variables.

You should go and take a look if you are still looking for this, or if any other person is looking for a good TTS.

Disclaimer: I don't work for IBM or anything related to this product, I just found it impressive!

Sapling