NVIDIA releases open-weight speech transcription model Nemotron 3.5 Transcribe
Matched fieldsTitle
View story:NVIDIA Releases Open-Weight Speech Transcription Model Nemotron 3.5 Transcribe
←Search results
Search “Speech”
Block releases full-duplex speech model Dessa
Block's AI research lab has released the full-duplex speech model Dessa, opening a waitlist as a research preview. According to MarkTechPost, the model was trained only on human voice conversation audio, without using text or pretrained models, and can run locally on a MacBook Pro M4 Max or higher configuration, faster than real time; training used one NVIDIA GB200 NVL72 (72 GPUs). No benchmark scores, parameter count, weights, paper, or API have been released so far.
Matched fieldsTitle
Block releases full-duplex speech model Dessa
Block's AI research lab has released the full-duplex speech model Dessa, opening a waitlist as a research preview. According to MarkTechPost, the model was trained only on human voice conversation audio, without using text or pretrained models, and can run locally on a MacBook Pro M4 Max or higher configuration, faster than real time; training used one NVIDIA GB200 NVL72 (72 GPUs). No benchmark scores, parameter count, weights, paper, or API have been released so far.
Matched fieldsTitle
Block releases full-duplex speech model Dessa
Block's internal AI research lab released the full-duplex speech-to-speech model Dessa on October 23. According to Unite.AI, the model was trained entirely from scratch on human conversational speech, can listen and speak simultaneously, and natively perceives emotion, sarcasm, and laughter; its inference is faster than real time and it can run locally on a MacBook Pro M4 Max or higher configuration, with the team completing training on a single NVIDIA GB200 NVL72. Block has released demo recordings and a public waitlist, and has opened early access to a small number of AI safety researchers. Other reports note that the model does not rely on a text intermediary and supports full-duplex conversation with the ability to interrupt and interject at any time, and that training consumes hundreds of times fewer tokens than large language models, but the author points out that this is currently only a small-scale research preview from Block's internal lab, the demos were selected by the company, and questions remain about how pure audio models perform on complex multi-step logical reasoning.
Block's internal AI research lab released the full-duplex speech-to-speech model Dessa on October 23. According to Unite.AI, the model was trained entirely from scratch on human conversational speech, can listen and speak simultaneously, and natively perceives emotion, sarcasm, and laughter; its inference is faster than real time and it can run locally on a MacBook Pro M4 Max or higher configuration, with the team completing training on a single NVIDIA GB200 NVL72. Block has released demo record
Matched fieldsTitle
Block releases speech model Dessa
Block's internal AI research lab released the full-duplex speech-to-speech model Dessa on October 23. According to Unite.AI, the model was trained entirely from scratch on human conversational speech, can listen and speak simultaneously, and natively perceives emotion, sarcasm, and laughter; its inference is faster than real time and it can run locally on a MacBook Pro M4 Max or higher configuration, with the team completing training on a single NVIDIA GB200 NVL72. Block has released demo recordings and a public waitlist, and has opened early access to a small number of AI safety researchers. Other reports note that the model does not rely on a text intermediary and supports full-duplex conversation with the ability to interrupt and interject at any time, and that training consumes hundreds of times fewer tokens than large language models, but the author points out that this is currently only a small-scale research preview from Block's internal lab, the demos were selected by the company, and questions remain about how pure audio models perform on complex multi-step logical reasoning.
Matched fieldsTitle
ElevenLabs releases the Eleven Realtime v1 speech-to-speech model
On October 20, 2026, ElevenLabs released the Eleven Realtime series of speech-to-speech models, comprising v1 Mini for low-cost natural conversation and v1 Max for complex tasks. According to the ElevenLabs blog, both support more than 90 languages and can access its over 17,000 voices; an independent evaluation by Artificial Analysis shows that v1 Max answered 98.8% of Big Bench Audio speech reasoning questions correctly and began speaking in an average of 0.57 seconds, while v1 Mini scored 75.9% and 0.62 seconds, respectively. The API is compatible with the OpenAI Realtime API, so existing integrations need only change the endpoint and model name, and models can also be selected directly for deployment in ElevenAgents. On October 22, Zhidongxi reported that the two models currently support only WebSocket connections; in its testing, an assistant built with Architect could modify Agent settings by voice, but the Chinese accent was noticeable, responses tended to be long, and latency was relatively high.
On October 20, 2026, ElevenLabs released the Eleven Realtime series of speech-to-speech models, comprising v1 Mini for low-cost natural conversation and v1 Max for complex tasks. According to the ElevenLabs blog, both support more than 90 languages and can access its over 17,000 voices; an independent evaluation by Artificial Analysis shows that v1 Max answered 98.8% of Big Bench Audio speech reasoning questions correctly and began speaking in an average of 0.57 seconds, while v1 Mini scored 75.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle
Mistral releases the Voxtral 3 speech model series
On October 21, 2026, Mistral released the Voxtral 3 speech model series, including one text-to-speech model and three speech-to-text models: Small Transcribe 3, Mini Transcribe 3, and Mini Transcribe Realtime 3. Artificial Analysis's evaluation shows that Voxtral Small Transcribe 3 ranks 3rd on the speech-to-text leaderboard with a 2.1% AA-WER Index, ahead of ElevenLabs Scribe v2 at 2.2% and Grok Voice Transcribe 2.0 at 2.3%; Voxtral Mini Transcribe 3 ranks 5th at 2.2%. Voxtral 3 TTS has an Elo of 1,218 in the provider voice arena, ranking 12th among 98 models, and is priced at $13 per million characters. There is currently no further evidence-based development.
Matched fieldsTitle
View story:Mistral releases the Voxtral 3 speech model series
Ant Ling Open-Sources the Ming-3.0 Speech Series, Five Models in Total
On October 20, 2026, Ant Ling (inclusionAI) open-sourced the Ming-3.0 speech series on GitHub, offering three series—speech synthesis, audio understanding and dialogue, and speech recognition—for a total of five models. Among them, Ming-3.0-tts includes a 0.5B dense version and a tiny MoE version based on Ling V3 with 7.9B total parameters and 1.3B activated parameters, supporting voice cloning, text-designed timbres, and multilingual synthesis; Ming-3.0-audio-flash uses a 126B-parameter MoE architecture with 6.5B activated parameters, and there is also a tiny version with 9.3B parameters and 2.7B activated parameters, covering multi-dialect accent recognition, long audio understanding, and end-to-end speech dialogue, under the MIT license. On the same day, vLLM announced that vLLM-Omni would provide support on the day of release, and Ant Ling thanked it and said deployment would be more convenient; atomic.chat will also integrate Ming-3.0 into local AI workflows. Artificial Analysis published an evaluation stating that Ming-3.0-tts ranks first among open-weight models in the controlled speech TTS Arena, and its pronunciation robustness of 93.2% ties for first among 31 models. On October 22, a blogger said they planned to trial-run the 0.5B version locally; on October 23, Artificial Analysis said it achieved top-tier TTS quality with 0.5B parameters.
On October 20, 2026, Ant Ling (inclusionAI) open-sourced the Ming-3.0 speech series on GitHub, offering three series—speech synthesis, audio understanding and dialogue, and speech recognition—for a total of five models. Among them, Ming-3.0-tts includes a 0.5B dense version and a tiny MoE version based on Ling V3 with 7.9B total parameters and 1.3B activated parameters, supporting voice cloning, text-designed timbres, and multilingual synthesis; Ming-3.0-audio-flash uses a 126B-parameter MoE arc
Matched fieldsTitle
ElevenLabs releases speech-to-speech model Eleven Realtime v1
On October 20, 2026, ElevenLabs released the Eleven Realtime series of speech-to-speech models, comprising v1 Mini for low-cost natural conversation and v1 Max for complex tasks. According to the ElevenLabs blog, both support more than 90 languages and can access its over 17,000 voices; an independent evaluation by Artificial Analysis shows that v1 Max answered 98.8% of Big Bench Audio speech reasoning questions correctly and began speaking in an average of 0.57 seconds, while v1 Mini scored 75.9% and 0.62 seconds, respectively. The API is compatible with the OpenAI Realtime API, so existing integrations need only change the endpoint and model name, and models can also be selected directly for deployment in ElevenAgents. On October 22, Zhidongxi reported that the two models currently support only WebSocket connections; in its testing, an assistant built with Architect could modify Agent settings by voice, but the Chinese accent was noticeable, responses tended to be long, and latency was relatively high.
Matched fieldsTitle
View story:ElevenLabs releases the Eleven Realtime v1 speech-to-speech model
Ant Ling Open-Sources the Ming-3.0 Speech Series Models
On October 20, 2026, Ant Ling (inclusionAI) open-sourced the Ming-3.0 speech series on GitHub, offering three series—speech synthesis, audio understanding and dialogue, and speech recognition—for a total of five models. Among them, Ming-3.0-tts includes a 0.5B dense version and a tiny MoE version based on Ling V3 with 7.9B total parameters and 1.3B activated parameters, supporting voice cloning, text-designed timbres, and multilingual synthesis; Ming-3.0-audio-flash uses a 126B-parameter MoE architecture with 6.5B activated parameters, and there is also a tiny version with 9.3B parameters and 2.7B activated parameters, covering multi-dialect accent recognition, long audio understanding, and end-to-end speech dialogue, under the MIT license. On the same day, vLLM announced that vLLM-Omni would provide support on the day of release, and Ant Ling thanked it and said deployment would be more convenient; atomic.chat will also integrate Ming-3.0 into local AI workflows. Artificial Analysis published an evaluation stating that Ming-3.0-tts ranks first among open-weight models in the controlled speech TTS Arena, and its pronunciation robustness of 93.2% ties for first among 31 models. On October 22, a blogger said they planned to trial-run the 0.5B version locally; on October 23, Artificial Analysis said it achieved top-tier TTS quality with 0.5B parameters.
Matched fieldsTitle
View story:Ant Ling Open-Sources the Ming-3.0 Speech Series, Five Models in Total
Matt Turck says open-source voice AI welcomes a small on-device SOTA TTS model suite
Matt Turck reposted and commented that a small on-device SOTA text-to-speech model suite has emerged in the open-source voice AI space. According to related reports, Gradium has open-sourced the Phonon on-device speech synthesis model suite, with all model parameters under 50m, focusing on multilingual naturalness and accuracy, and claiming to offer the broadest inference support to date; among them, Phonon-31m is released under the Apache 2.0 license. Currently, this news has been reposted by Matt Turck, with no further developments yet.
Matt Turck reposted and commented that a small on-device SOTA text-to-speech model suite has emerged in the open-source voice AI space. According to related reports, Gradium has open-sourced the Phonon on-device speech synthesis model suite, with all model parameters under 50m, focusing on multilingual naturalness and accuracy, and claiming to offer the broadest inference support to date; among them, Phonon-31m is released under the Apache 2.0 license. Currently, this news has been reposted by M
Matched fieldsTitle
Matt Turck says open-source voice AI welcomes a small on-device SOTA TTS model suite
Matt Turck reposted and commented that a small on-device SOTA text-to-speech model suite has emerged in the open-source voice AI space. According to related reports, Gradium has open-sourced the Phonon on-device speech synthesis model suite, with all model parameters under 50m, focusing on multilingual naturalness and accuracy, and claiming to offer the broadest inference support to date; among them, Phonon-31m is released under the Apache 2.0 license. Currently, this news has been reposted by Matt Turck, with no further developments yet.
Matched fieldsTitle
View story:Matt Turck says open-source voice AI welcomes a small on-device SOTA TTS model suite
Mistral releases the Voxtral 3 speech model series
On October 21, 2026, Mistral released the Voxtral 3 speech model series, including one text-to-speech model and three speech-to-text models: Small Transcribe 3, Mini Transcribe 3, and Mini Transcribe Realtime 3. Artificial Analysis's evaluation shows that Voxtral Small Transcribe 3 ranks 3rd on the speech-to-text leaderboard with a 2.1% AA-WER Index, ahead of ElevenLabs Scribe v2 at 2.2% and Grok Voice Transcribe 2.0 at 2.3%; Voxtral Mini Transcribe 3 ranks 5th at 2.2%. Voxtral 3 TTS has an Elo of 1,218 in the provider voice arena, ranking 12th among 98 models, and is priced at $13 per million characters. There is currently no further evidence-based development.
On October 21, 2026, Mistral released the Voxtral 3 speech model series, including one text-to-speech model and three speech-to-text models: Small Transcribe 3, Mini Transcribe 3, and Mini Transcribe Realtime 3. Artificial Analysis's evaluation shows that Voxtral Small Transcribe 3 ranks 3rd on the speech-to-text leaderboard with a 2.1% AA-WER Index, ahead of ElevenLabs Scribe v2 at 2.2% and Grok Voice Transcribe 2.0 at 2.3%; Voxtral Mini Transcribe 3 ranks 5th at 2.2%. Voxtral 3 TTS has an Elo
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle
English translation is being prepared.
Matched fieldsTitle