# Mark II voice change
**URL:** https://community.openconversational.ai/t/mark-ii-voice-change/12654
**Category:** Archive - Former Random Mycroft Category
**Created:** [November 1, 2022, 5:28pm UTC](https://community.openconversational.ai/t/mark-ii-voice-change/12654 "2022-11-01T17:28:46Z")
**Posts on this page:** 7
**Page:** 1
### Author:  [@colin](https://community.openconversational.ai/u/colin)
#### Post date: [November 1, 2022, 5:28pm UTC](https://community.openconversational.ai/t/mark-ii-voice-change/12654/1 "2022-11-01T17:28:46Z")
Am a noob here with mycroft.
Wanted a female voice for the markII.
Checked at ~/.local/share/mycroft/mimic3/voices and only had en\_US/cmu-arctic\_low and en\_UK/apope\_low.
Tried a mimic3 --voice ‘en\_US/cmu-arctic\_low’ but didn’t work ?? so downloaded the rest of the en\_US voice files.
mimic3-download ‘en\_US/\*’
This gave me cmu-arctic\_low, hifi-tts\_low, ljspeech\_low, m-ailabs\_low, vctk\_low
Tried all thru the mimic3 cmd, but only ljspeech\_low worked, perhaps because it only has a default “speaker” ?
mimic3 --voice ‘en\_US/ljspeech\_low’ --debug ‘My hovercraft is full of eels.’
Anyways, changed the .config/mycroft/mycroft\_conf file to:
“voice”: “en\_US/ljspeech\_low”
and rebooted and now have a female voice.
However, occasionally (perhaps when there’s an error ?), Mr Pope comes back on !
Anyone know if I have to change the voice in some other area ? Wouldn’t have thought so.
Mr Pope obviously does not like being evicted 🙂
---
### Author:  [@synesthesiam](https://community.openconversational.ai/u/synesthesiam)
#### Post date: [November 1, 2022, 8:03pm UTC](https://community.openconversational.ai/t/mark-ii-voice-change/12654/2 "2022-11-01T20:03:31Z")
> [@colin](#):
>
> However, occasionally (perhaps when there’s an error ?), Mr Pope comes back on !
This is due to the TTS cache. We pre-cached some sentences with Mr. Pope in `/opt/mark-ii-product/docker/files/opt/mycroft/preloaded_cache/Mimic3` and then there is the dynamically generated cache in `/tmp/mycroft/cache/tts`. Clearing both caches will ensure that your selected voice is always used.
---
### Author:  [@colin](https://community.openconversational.ai/u/colin)
#### Post date: [November 1, 2022, 11:17pm UTC](https://community.openconversational.ai/t/mark-ii-voice-change/12654/3 "2022-11-01T23:17:58Z")
Thanks synesthesiam, removed those files from the 2 areas. So far so good.
(As I removed them, looked out the window and saw Mr. Pope exiting the building with a sack labelled “stderr” on his back, and .wavs babelling "sorry I don’t understand’ “you’re not paired” “is your computer plugged in” “help” etc.
Kudos to him tho, for donating his time and expertise to TTS.
---
### Author:  [@synesthesiam](https://community.openconversational.ai/u/synesthesiam)
#### Post date: [November 2, 2022, 2:37pm UTC](https://community.openconversational.ai/t/mark-ii-voice-change/12654/4 "2022-11-02T14:37:34Z")
Indeed! I hope in the far future that Mr. Pope will be the voice of the Enterprise.
---
### Author:  [@ecs](https://community.openconversational.ai/u/ecs)
#### Post date: [November 29, 2022, 12:14am UTC](https://community.openconversational.ai/t/mark-ii-voice-change/12654/5 "2022-11-29T00:14:39Z")
Quick question, does this work for Mycroft Dinkum, or had you put the Classic Core version on your Mark II?
---
### Author:  [@colin](https://community.openconversational.ai/u/colin)
#### Post date: [November 29, 2022, 1:44am UTC](https://community.openconversational.ai/t/mark-ii-voice-change/12654/6 "2022-11-29T01:44:32Z")
ecs,
nope this was on dinkum, and it works good.
I did try Classic core on the mk2, but ended up with trying to sort out it’s recognition that this is a mk2 enclosure. So temp abandonded that
---
### Author:  [@ecs](https://community.openconversational.ai/u/ecs)
#### Post date: [December 1, 2022, 4:39am UTC](https://community.openconversational.ai/t/mark-ii-voice-change/12654/7 "2022-12-01T04:39:26Z")
> [@colin](#):
>
> Tried all thru the mimic3 cmd, but only ljspeech\_low worked, perhaps because it only has a default “speaker” ?
Does anyone have ideas about this? I think this is correct, in that the only voices that work have only one speaker. Is there perhaps a way to convert a single speaker from an existing voice into a “new” voice with just that speaker? Alternatively, how do you get the engine to recognize a specific speaker?