I've been using http://www.oddcast.com/home/demos/tts/tts_example.php?sitepa%20l for a few years and have been quite happy with it. However I'm not able to use it anymore as there appears to be some kind of conflict between Firefox and the QuickTime plugin it uses.
If anyone knows an easy way around this, that would be great. Or if you know of another similar site, that would also work. I use it to create audio files of sentences (usually Spanish and French, and sometimes Japanese) that I then put into Anki. I've tried Google Translate a few times, and the audio always sounds funny.
Thanks
Online text-to-speech site for various languages?
- kaizen
- Posts: 7
- Joined: Sat Mar 05, 2016 12:58 am
- x 1
Online text-to-speech site for various languages?
0 x
"Everything we want is on the other side of fear."
George Addair
George Addair
- Rebecca
- Yellow Belt
- Posts: 67
- Joined: Fri Aug 14, 2015 11:08 am
- Location: UK
- Languages: English (N), French (Beginner)
- Language Log: viewtopic.php?f=15&t=1821
- x 125
Re: Online text-to-speech site for various languages?
I use the Awesome TTS Anki add-on which can automatically add audio to your Anki cards. For most languages there are quite a few different 'voices' you can choose from. I personally use the Manon voice from the Acapela group for French. It is much easier than generating individual sentences and then adding them to all your cards manually!
1 x
- Jar-Ptitsa
- Brown Belt
- Posts: 1000
- Joined: Sun Jul 19, 2015 1:13 pm
- Location: London
- Languages: Belgian French (N)
I can speak: Dutch, German, English, Spanish and understand Italian, Portuguese, Wallonian, Afrikaans, but not always correctly. - x 652
Re: Online text-to-speech site for various languages?
In my school we had text-to-speech options instead of reading, if we wanted / needed this. I don't remember its name, but anyway, I finsihed school about 3 or 4 years ago, so the technology would be old now.
Ivona has many languages and you can type a short text https://www.ivona.com/
This can read different things and there are many options for the langauge and reader http://www.naturalreaders.com/index.html
Ivona has many languages and you can type a short text https://www.ivona.com/
This can read different things and there are many options for the langauge and reader http://www.naturalreaders.com/index.html
0 x
I am Jar-ptitsa and my Hawaiian name is ʻā ʻaia. Please correct my mistakes in all the languages. Thank you very much.
: Spanish grammar
: Spanish vocabulary
: Spanish grammar
: Spanish vocabulary
- jeff_lindqvist
- Black Belt - 3rd Dan
- Posts: 3167
- Joined: Sun Aug 16, 2015 9:52 pm
- Languages: sv, en
de, es
ga, eo
---
fi, yue, ro, tp, cy, kw, pt, sk - Language Log: viewtopic.php?f=15&t=2773
- x 10597
Re: Online text-to-speech site for various languages?
Rebecca wrote:I use the Awesome TTS Anki add-on which can automatically add audio to your Anki cards. For most languages there are quite a few different 'voices' you can choose from. I personally use the Manon voice from the Acapela group for French. It is much easier than generating individual sentences and then adding them to all your cards manually!
Same here. I use the on-the-fly option instead of making individual files (gigantic deck!), and so far, it has been pretty accurate for Mandarin and Cantonese (my only TTS languages at the moment). I wouldn't be surprised if it worked even better for other languages.
1 x
Leabhair/Greannáin léite as Gaeilge:
Ar an seastán oíche:Oileán an Órchiste
Duolingo - finished trees: sp/ga/de/fr/pt/it
Finnish with extra pain :
Llorg Blog - Wiki - Discord
Ar an seastán oíche:
Duolingo - finished trees: sp/ga/de/fr/pt/it
Finnish with extra pain :
Llorg Blog - Wiki - Discord
- kaizen
- Posts: 7
- Joined: Sat Mar 05, 2016 12:58 am
- x 1
Re: Online text-to-speech site for various languages?
Thanks to all of you for your replies. I'll try each of those out and see which works best for me.
0 x
"Everything we want is on the other side of fear."
George Addair
George Addair
- Iversen
- Black Belt - 4th Dan
- Posts: 4787
- Joined: Sun Jul 19, 2015 7:36 pm
- Location: Denmark
- Languages: Monolingual travels in Danish, English, German, Dutch, Swedish, French, Portuguese, Spanish, Catalan, Italian, Romanian and (part time) Esperanto
Ahem, not yet: Norwegian, Afrikaans, Platt, Scots, Russian, Serbian, Bulgarian, Albanian, Greek, Latin, Irish, Indonesian and a few more... - Language Log: viewtopic.php?f=15&t=1027
- x 15049
Re: Online text-to-speech site for various languages?
I have used acapela a lot .... though not as much the last year or so where my music collection has been distracting me.
0 x
-
- Green Belt
- Posts: 261
- Joined: Sat Aug 22, 2015 3:20 pm
- Location: England
- Languages: English (N), Icelandic (B2 reading, B1 listening), Hebrew (basic)
- Language Log: viewtopic.php?f=15&t=1139
- x 481
Re: Online text-to-speech site for various languages?
The Icelandic national broadcaster uses ReadSpeaker, which sounds amazingly natural. It's pricy but might be worth it depending on how much you're planning to use it. You can try out passages of up to 250 characters online.
http://textaid.readspeaker.com
http://textaid.readspeaker.com
0 x
-
- Green Belt
- Posts: 261
- Joined: Sat Aug 22, 2015 3:20 pm
- Location: England
- Languages: English (N), Icelandic (B2 reading, B1 listening), Hebrew (basic)
- Language Log: viewtopic.php?f=15&t=1139
- x 481
Re: Online text-to-speech site for various languages?
Iversen wrote:I have used acapela a lot .... though not as much the last year or so where my music collection has been distracting me.
How on earth did acapela decide to offer Faroese but not Icelandic?? I just have to wonder.
1 x
-
- Orange Belt
- Posts: 228
- Joined: Sun Feb 26, 2017 4:01 pm
- Languages: English (native); strong reading skills - Russian, Spanish, French, Italian, German, Serbo-Croatian, Macedonian, Bulgarian, Slovene, Farsi; fair reading skills - Polish, Czech, Dutch, Esperanto, Portuguese; beginner/rusty - Swedish, Norwegian, Danish
- x 590
Re: Online text-to-speech site for various languages?
I don't know if it's been addressed here before, but Amazon Web Services' Polly at https://console.aws.amazon.com/polly/ho ... sizeSpeech has some very high-quality voices, 47 of them, for a couple dozen languages. This is a relatively new AWS offering, I think since the end of last year. The demo page at the above URL lets you hear the speech online, or save it to an MP3. You can process up to 5 million characters per month for free; after that it's 4/10 of a cent per minute of speech. The AWS blog announcing Polly estimated that this would equate to $2.40 for the full text of The Adventures of Huckleberry Finn. I personally am not likely to go beyond 5 million characters for personal use in a single month, but if I somehow do, it will still be very inexpensive.
Amazon provides sample programs for using Polly's API, including a script in Python for running a local TTS server on your own machine that you can call from your Web browser. There is a sample command for using the AWS command line interface to get an MP3 file from Polly:
Polly obviously requires that you have an active Amazon/AWS account, and if you're calling it programmatically you'll probably need to have your AWS credentials stored on your own machine, which takes a few steps but is not that difficult. I'm in the process of integrating Polly into my own software now.
The most significant limitation seems to be a 1500-character limit per call; but there are already a couple of sample programs on GitHub showing how to split a longer text into chunks and then recombine the audio. That might be irrelevant anyway for some applications, like getting an audio clip for a flashcard.
Amazon provides sample programs for using Polly's API, including a script in Python for running a local TTS server on your own machine that you can call from your Web browser. There is a sample command for using the AWS command line interface to get an MP3 file from Polly:
Code: Select all
aws polly synthesize-speech \
--output-format mp3 --voice-id Joanna \
--text "Hello my name is Joanna." \
joanna.mp3
Polly obviously requires that you have an active Amazon/AWS account, and if you're calling it programmatically you'll probably need to have your AWS credentials stored on your own machine, which takes a few steps but is not that difficult. I'm in the process of integrating Polly into my own software now.
The most significant limitation seems to be a 1500-character limit per call; but there are already a couple of sample programs on GitHub showing how to split a longer text into chunks and then recombine the audio. That might be irrelevant anyway for some applications, like getting an audio clip for a flashcard.
2 x
Return to “Language Programs and Resources”
Who is online
Users browsing this forum: No registered users and 2 guests