Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
tts
Follow
Hide
Posts
Left menu
ð
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
Making open-source text to speech sound right: ranked voices, text normalization and one engine for Python and the browser
Asad Shehzad
Asad Shehzad
Asad Shehzad
Follow
Oct 16
Making open-source text to speech sound right: ranked voices, text normalization and one engine for Python and the browser
#
tts
#
python
#
opensource
#
javascript
Comments
Add Comment
3 min read
Switch-Point Prosody: Why AI Voices Break Where Pakistani Ads Switch Languages
Muhammad Usman SU92-BSAIM-F25-025
Muhammad Usman SU92-BSAIM-F25-025
Muhammad Usman SU92-BSAIM-F25-025
Follow
Oct 14
Switch-Point Prosody: Why AI Voices Break Where Pakistani Ads Switch Languages
#
ai
#
tts
#
speech
#
research
Comments
Add Comment
3 min read
āļŦāļļāđāļāđāļŠāļĩāļĒāļ AI āļāļąāļ§āļāļĩāđāļāļđāļāđāļāļĒāđāļĄāđāļāļāļ§āđāļē ElevenLabs 25 āđāļāđāļē āļāļĢāļīāļāđāļŦāļĄ? āđāļāļ° VoxCPM2 āļŠāļēāļĄāļŦāļĄāļ·āđāļāđāļāļāļāļąāļāļāļēāļ§
Nokka
Nokka
Nokka
Follow
Oct 13
āļŦāļļāđāļāđāļŠāļĩāļĒāļ AI āļāļąāļ§āļāļĩāđāļāļđāļāđāļāļĒāđāļĄāđāļāļāļ§āđāļē ElevenLabs 25 āđāļāđāļē āļāļĢāļīāļāđāļŦāļĄ? āđāļāļ° VoxCPM2 āļŠāļēāļĄāļŦāļĄāļ·āđāļāđāļāļāļāļąāļāļāļēāļ§
#
ai
#
tts
#
opensource
#
thai
Comments
Add Comment
3 min read
My TTS read a whole novel. The model was the most reliable part of the pipeline
Servin Osmanov
Servin Osmanov
Servin Osmanov
Follow
Oct 9
My TTS read a whole novel. The model was the most reliable part of the pipeline
#
ai
#
tts
#
asr
#
machinelearning
Comments
Add Comment
16 min read
GeminiTTS: Gemini 3.8 TTS Online for Single-Voice and Two-Speaker Dialogue
leony
leony
leony
Follow
Oct 7
GeminiTTS: Gemini 3.8 TTS Online for Single-Voice and Two-Speaker Dialogue
#
ai
#
tts
#
speech
#
sideprojects
Comments
Add Comment
2 min read
Paxa TTS Flash āđāļĄāđāļāļĨ TTS āđāļŠāļĩāļĒāļāđāļāļĒ 32 āđāļŠāļĩāļĒāļ āđāļĨāļ°āđāļāļ·āđāļāļāļŦāļĨāļąāļāļāļĩāđāļāļĢāļ§āļāļŠāļāļāđāļāđ
Nokka
Nokka
Nokka
Follow
Sep 19
Paxa TTS Flash āđāļĄāđāļāļĨ TTS āđāļŠāļĩāļĒāļāđāļāļĒ 32 āđāļŠāļĩāļĒāļ āđāļĨāļ°āđāļāļ·āđāļāļāļŦāļĨāļąāļāļāļĩāđāļāļĢāļ§āļāļŠāļāļāđāļāđ
#
ai
#
tts
#
thai
#
opensource
Comments
Add Comment
3 min read
-preset slow bought 0.16%. Ten ffmpeg settings measured on two ARM cores.
Obole
Obole
Obole
Follow
Sep 17
-preset slow bought 0.16%. Ten ffmpeg settings measured on two ARM cores.
#
ai
#
performance
#
python
#
tts
Comments
Add Comment
8 min read
JaiTTS āđāļāļĨāļāđāļŠāļĩāļĒāļāđāļāļĒāļāļĩāđāļāļ°āđāļāļāđāļĄāđāļāļāļ§āđāļēāļĄāļāļļāļĐāļĒāđ āđāļĨāļ°āđāļāļīāļāđāļāđāļāļĢāļĩ
Nokka
Nokka
Nokka
Follow
Sep 16
JaiTTS āđāļāļĨāļāđāļŠāļĩāļĒāļāđāļāļĒāļāļĩāđāļāļ°āđāļāļāđāļĄāđāļāļāļ§āđāļēāļĄāļāļļāļĐāļĒāđ āđāļĨāļ°āđāļāļīāļāđāļāđāļāļĢāļĩ
#
tts
#
thai
#
ai
#
opensource
Comments
Add Comment
2 min read
Splitting text into sentences costs Kokoro 8% and Piper nothing
Obole
Obole
Obole
Follow
Sep 16
Splitting text into sentences costs Kokoro 8% and Piper nothing
#
ai
#
performance
#
python
#
tts
Comments
Add Comment
4 min read
What I learned building speech tech for a language with zero datasets
Servin Osmanov
Servin Osmanov
Servin Osmanov
Follow
Sep 10
What I learned building speech tech for a language with zero datasets
#
ai
#
lm
#
tts
#
programming
Comments
Add Comment
10 min read
OmniVoice āđāļĄāđāļāļĨ TTS 600+ āļ āļēāļĐāļē āđāļāļĨāļāđāļŠāļĩāļĒāļāļāļēāļāļāļĨāļīāļ 3 āļ§āļīāļāļēāļāļĩ āđāļāļīāļāļāļāļĢāđāļŠāļāļĢāļĩ
Nokka
Nokka
Nokka
Follow
Sep 6
OmniVoice āđāļĄāđāļāļĨ TTS 600+ āļ āļēāļĐāļē āđāļāļĨāļāđāļŠāļĩāļĒāļāļāļēāļāļāļĨāļīāļ 3 āļ§āļīāļāļēāļāļĩ āđāļāļīāļāļāļāļĢāđāļŠāļāļĢāļĩ
#
ai
#
tts
#
opensource
#
thai
Comments
Add Comment
1 min read
Three real sessions on a CPU voice agent API
Daniel Varela
Daniel Varela
Daniel Varela
Follow
Sep 24
Three real sessions on a CPU voice agent API
#
voiceai
#
voiceagents
#
ai
#
tts
Comments
Add Comment
1 min read
Introducing Paxa Labs
Paxa Labs
Paxa Labs
Paxa Labs
Follow
Aug 28
Introducing Paxa Labs
#
ai
#
tts
#
api
#
thai
5
 reactions
Comments
2
 comments
3 min read
Vowel estimation accuracy varies by pronunciation order and duration: Creating TTS evaluation data and two measurement pitfalls
orca forge
orca forge
orca forge
Follow
Sep 25
Vowel estimation accuracy varies by pronunciation order and duration: Creating TTS evaluation data and two measurement pitfalls
#
tts
Comments
Add Comment
6 min read
I Built a Free MIT Audio Engine for Expo Because Background Audio Should Not Require a Commercial License
Mark Melton
Mark Melton
Mark Melton
Follow
Aug 19
I Built a Free MIT Audio Engine for Expo Because Background Audio Should Not Require a Commercial License
#
reactnative
#
opensource
#
mobile
#
tts
Comments
Add Comment
4 min read
ð
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account
