A new, open source text-to-speech model called Dia has arrived to challenge ElevenLabs, OpenAI and more https://bit.ly/445O7Au #AI #voices #OpenSource
Recent searches
Search options
#voices
0 posts0 participants0 posts today
A new, open source text-to-speech model called Dia has arrived to challenge ElevenLabs, OpenAI and more https://bit.ly/445O7Au #AI #voices #OpenSource
![Text Shot: Dia supports nuanced features like emotional tone, speaker tagging, and nonverbal audio cues—all from plain text.
Users can mark speaker turns with tags like [S1] and [S2], and include cues like (laughs), (coughs), or (clears throat) to enrich the resulting dialogue with nonverbal behaviors.
These tags are correctly interpreted by Dia during generation—something not reliably supported by other available models, according to the company’s examples page.
The model is currently English-only and not tied to any single speaker’s voice, producing different voices per run unless users fix the generation seed or provide an audio prompt. Audio conditioning, or voice cloning, lets users guide speech tone and voice likeness by uploading a sample clip.](https://files.techhub.social/media_attachments/files/114/383/277/983/275/082/original/b82014d68e7d81f0.png "Text Shot: Dia supports nuanced features like emotional tone, speaker tagging, and nonverbal audio cues—all from plain text.
Users can mark speaker turns with tags like [S1] and [S2], and include cues like (laughs), (coughs), or (clears throat) to enrich the resulting dialogue with nonverbal behaviors.
These tags are correctly interpreted by Dia during generation—something not reliably supported by other available models, according to the company’s examples page.
The model is currently English-only and not tied to any single speaker’s voice, producing different voices per run unless users fix the generation seed or provide an audio prompt. Audio conditioning, or voice cloning, lets users guide speech tone and voice likeness by uploading a sample clip.")
The #People - They are the #True #Power of the #Nation Their #Voices will get #Louder & the #Protests will get #Bigger until the #Constitution and the #Law are #Respected
RE: https://bsky.app/profile/did:plc:w26edbpr2uswd43ys4a7jngd/post/3lndqbxv2mc25
Bluesky SocialBluesky
So lets make it 100% To take back #Democracy Everyone #RiseUp #Attend the weekends #Protests in your state. Be the force of good and save #America Be the #Resistance Get your #Voices #Heard
RE: https://bsky.app/profile/did:plc:gaqyvusq4dze2qxaytydob4n/post/3lmscudg4722w
Bluesky SocialBluesky
Move over, Alexa: Amazon launches new realtime voice model Nova Sonic for third-party enterprise development https://venturebeat.com/ai/move-over-alexa-amazon-launches-new-realtime-voice-model-nova-sonic-for-third-party-enterprise-development/ #AI #voices
Move over, Alexa: Amazon launches new realtime voice model Nova Sonic for third-party enterprise development https://venturebeat.com/ai/move-over-alexa-amazon-launches-new-realtime-voice-model-nova-sonic-for-third-party-enterprise-development/ #AI #voices
Sesame, the startup behind the viral virtual assistant Maya, releases its base AI model | TechCrunch https://techcrunch.com/2025/03/13/sesame-the-startup-behind-the-viral-virtual-assistant-maya-releases-its-base-ai-model/ #AI #voices
Sesame, the startup behind the viral virtual assistant Maya, releases its base AI model | TechCrunch https://techcrunch.com/2025/03/13/sesame-the-startup-behind-the-viral-virtual-assistant-maya-releases-its-base-ai-model/ #AI #voices
#Amazonwatch was in the #courtroom for the #SLAPP trial against @greenpeace It was a sham: biased jurors, judicial misconduct, and #erasure of #Indigenous #voices.
Read why this matters for us all.
https://amazonwatch.org/news/2025/0403-big-oils-lawfare-attacks-on-advocacy-and-accountability
#StandWithStandingRock #DefendFreeSpeech
Amazon Watch · Big Oil’s “Lawfare” Attacks on Advocacy and Accountability | Amazon WatchThis is not justice. Greenpeace will appeal, and they need all of us to mobilize in a massive international movement in support of their efforts to expose this sham trial.
amzn.toAmazon.fr : In My Hands: Memories of a Holocaust Rescuer
This Is Not About Antisemitism, Palestine, or Columbia. It’s Trump Dismantling the American Dream.
https://theintercept.com/2025/04/01/trump-ice-deport-students-immigrants-american-dream/
The Intercept · This Is Not About Antisemitism, Palestine, or Columbia. It’s Trump Dismantling the American Dream.
"In the world of #Palestinian activism, the plight of autistic people is often overlooked...Speaking about the plight of our #autistic friends and family members can loosen the clutches ever so slightly. In a world where Palestinians are constantly and aggressively silenced, these #voices [also] need to be heard."
https://www.middleeasteye.net/opinion/israeli-occupation-further-isolates-autistic-children-how
#autism #palestine #westbank
(#trauma also causes #neurodiversity as neuro pathways generate or reroute to respond, endure, and anticipate the new stimuli)
Middle East EyeHow the Israeli occupation further isolates autistic childrenLiving in the West Bank comes with myriad challenges, from navigating checkpoints to accessing treatment options
Groq and PlayAI just made voice AI sound way more human — here’s how https://bit.ly/4iOwOIG #AI #speech #voices
Groq and PlayAI just made voice AI sound way more human — here’s how https://bit.ly/4iOwOIG #AI #speech #voices
An international cohort of writers learn with and care for each other in Tokyo and beyond. https://www.japantimes.co.jp/community/2025/03/24/voices/mixed-race-identity-storytelling-workshop/?utm_medium=Social&utm_source=mastodon #community #voices #hafu #identity #mixedrace #writing #travelwriting #teaching
The Japan Times · A community of stories: Making space for reflection and dialogue in Tokyo and beyond
ElevenLabs AI is Bringing Salvador Dali Back to Life | ElevenLabs https://elevenlabs.io/blog/dalis-voice-how-ai-is-bringing-the-surrealist-back-to-life #AI #voices
ElevenLabs AI is Bringing Salvador Dali Back to Life | ElevenLabs https://elevenlabs.io/blog/dalis-voice-how-ai-is-bringing-the-surrealist-back-to-life #AI #voices
OpenAI’s new voice AI model gpt-4o-transcribe lets you add speech to your existing text apps in seconds https://bit.ly/4huaWkj #AI #voices
OpenAI’s new voice AI model gpt-4o-transcribe lets you add speech to your existing text apps in seconds https://bit.ly/4huaWkj #AI #voices