←Search results

Search “Speech”

By relevance · Total 1359 results Clear search

Tuesday

  3. SiliconANGLE

    Scaled Cognition Launches Customer Service Voice Model Voice

    Scaled Cognition has released Voice, a text-to-speech model that supports more than 25 languages and voice cloning, and can be accessed via API or deployed self-hosted. It focuses on accurately reading aloud details such as account numbers and addresses. Managed API pricing is $9 per million characters, while self-hosting costs $1 per million characters (excluding infrastructure). The company says that at a scale of 5 million characters, including infrastructure, the cost is about $13 per million characters, and it claims a speech generation latency of 70 milliseconds. Voice's Smart Pronunciation capability first determines the meaning of abbreviations and numbers before generating audio—for example, reading "Pay 1/2 by 1/2" as "pay half by January second"—and it can run without relying on APT or other large language models.

    Scaled Cognition has released Voice, a text-to-speech model that supports more than 25 languages and voice cloning, and can be accessed via API or deployed self-hosted. It focuses on accurately reading aloud details such as account numbers and addresses. Managed API pricing is $9 per million characters, while self-hosting costs $1 per million characters (excluding infrastructure). The company says that at a scale of 5 million characters, including infrastructure, the cost is about $13 per millio

    Matched fieldsTitle、Summary、Body

    #hot-signal#Model releases#Speech#English text is being prepared.
  4. AntLingAGI

    AntLing Ming-3.0 Speech Models Integrated into atomic.chat Local Workflow

    AntLingAGI thanks atomic.chat for integrating Ming-3.0 into local AI workflows, making open-source speech models more accessible. According to atomic.chat, Ming-3.0 comprises 5 open-source models covering speaking, listening, and speech transcription; its speech model ranks No. 1 among open-source models on Artificial Analysis, and the smallest version is only 0.5B.

    Matched fieldsTitle、Summary、Body

    #editorial#Product updates#Open-source ecosystem#Speech
  5. Ant LingSelected

    Ant Ling's Ming-3.0 Speech Models Get Day-0 Support in vLLM-Omni

    Ant Ling has open-sourced 5 speech models covering TTS, audio understanding, and ASR, with total parameter counts ranging from 0.5B to 126B (6.5B active parameters). vLLM announced that vLLM-Omni provided Ming-3.0 support on the day of release; Ant Ling thanked them for this and said deployment is now more convenient.

    Matched fieldsTitle、Summary

    #editorial#Product updates#English text is being prepared.#Open-source ecosystem
  11. AWS Machine Learning

    How Deepgram optimized large-scale speech AI with AWS Trainium

    Deepgram partnered with AWS to port the Nova-3 speech-to-text model to Trainium2, running 8 model replicas on a single trn2.3xlarge instance, achieving an 11%–70% increase in audio processed per dollar compared with the previous solution in offline batch processing scenarios. The team used TorchNeuron to complete the PyTorch port and tuned it through NKILib fused kernels and hand-written NKI kernels, among which the FFN kernel reduced latency by 2.0x, depthwise conv1d sped up by 1.5x, and the conv2d kernel unlocked batch sizes above 32.

    Nova-3 encoder and decoder compiled ahead of time to NEFFs and served by a data-parallel Rust runtime on AWS Trainium2

    Deepgram partnered with AWS to port the Nova-3 speech-to-text model to Trainium2, running 8 model replicas on a single trn2.3xlarge instance, achieving an 11%–70% increase in audio processed per dollar compared with the previous solution in offline batch processing scenarios. The team used TorchNeuron to complete the PyTorch port and tuned it through NKILib fused kernels and hand-written NKI kernels, among which the FFN kernel reduced latency by 2.0x, depthwise conv1d sped up by 1.5x, and the co

    Matched fieldsTitle、Summary、Body

    #lab#Tutorials / practice#English text is being prepared.#Speech

Monday

  1. Ant Ling

    Ant Ling Open-Sources the Ming-3.0 Series of 5 Speech Models

    Ant Ling has open-sourced 5 models in the Ming-3.0 series, covering three speech families: tts, audio, and asr. Ming-3.0-tts includes a 0.5B speech design and paralinguistic cue model and a Tiny 7.9B A1.3B long-speech model; Ming-3.0-audio includes a Flash 126B A6.5B understanding and tool model and a Tiny 9.3B A2.7B efficient dialogue model; Ming-3.0-asr is Tiny 8.6B A2B, aimed at dialects and context.

    Matched fieldsTitle、Summary、Body

    #editorial#Model releases#Open-source ecosystem#Speech
  3. ElevenLabs Blog

    How Content Creators Can Use Speech-to-Text: A Workflow Guide

    ElevenLabs has released a speech-to-text workflow guide for content creators, covering how to use speech-to-text to generate video captions, podcast show notes, searchable content libraries, and content translations. ElevenLabs Caption Generator can generate transcripts with word-level and character-level timestamps and export SRT and VTT files; the Scribe v2 model transcribes verbatim by default, and you can enable "Clean Transcript" in the Playground or switch to cleaned transcription via the no_verbatim parameter in the ElevenAPI.

    Speech to text for creators by the numbers. Caption and Scribe v2 statistics: 87% use captions, 98% accuracy, 90+ languages.

    ElevenLabs has released a speech-to-text workflow guide for content creators, covering how to use speech-to-text to generate video captions, podcast show notes, searchable content libraries, and content translations. ElevenLabs Caption Generator can generate transcripts with word-level and character-level timestamps and export SRT and VTT files; the Scribe v2 model transcribes verbatim by default, and you can enable "Clean Transcript" in the Playground or switch to cleaned transcription via the

    Matched fieldsTitle、Summary、Body

    #company#Tutorials / practice#Speech#Product updates
  4. Google Developers Blog

    Google Developers Blog publishes ADK voice agent tutorial: using streaming tools to eliminate silence

    Google Developers Blog published a step-by-step tutorial on how to build a voice agent with ADK and gemini-3.8-live that does not stay silent for long periods. The core approach is to change tool functions from return to yield to make them streaming tools, or to use FunctionTool's response_scheduling to deliver results when idle; in the sales report benchmark flow, the agent's time to first speech dropped from 14.4 seconds to 1.2 seconds. The tutorial also covers the stop_streaming cancellation mechanism, preventing duplicate calls, and the trade-offs among the three scheduling modes WHEN_IDLE, INTERRUPT, and SILENT. It requires google-adk >= 2.10.0 and uses run_live bidirectional sessions.

    option4_minimal_flow_diagram_1600x900

    Google Developers Blog published a step-by-step tutorial on how to build a voice agent with ADK and gemini-3.8-live that does not stay silent for long periods. The core approach is to change tool functions from return to yield to make them streaming tools, or to use FunctionTool's response scheduling to deliver results when idle; in the sales report benchmark flow, the agent's time to first speech dropped from 14.4 seconds to 1.2 seconds. The tutorial also covers the stop streaming cancellation

    Matched fieldsTitle、Summary、Body

    #engineering#Tutorials / practice#Speech#Agents

Saturday

  1. Unite.AI

    What Is a Native Audio Model? How Speech-to-Speech AI Skips the Transcription Step

    Native audio models process or generate acoustic representations directly, preserving information such as timing, intonation, and speaker cues that text transcription would discard. They are fundamentally different from the "transcribe to text first, then synthesize speech" pipeline: the latter changes the causal chain, and the evidence of success, the sources of cost, and the approach to risk control all differ. The article breaks down its workflow into five stages: converting waveforms into audio tokens, modeling speech and non-speech context, inferring semantics and dialogue state, generating audio tokens, and decoding natural speech.

    Native audio models process or generate acoustic representations directly, preserving information such as timing, intonation, and speaker cues that text transcription would discard. They are fundamentally different from the "transcribe to text first, then synthesize speech" pipeline: the latter changes the causal chain, and the evidence of success, the sources of cost, and the approach to risk control all differ. The article breaks down its workflow into five stages: converting waveforms into au

    Matched fieldsTitle、Summary、Body

    #hot-signal#Tutorials / practice#Speech