Loading video...

Video Failed to Load

Go Home

Fish Audio has released S2.1 Pro, its latest production voice model that is built for real-time conversational AI. S2.1 Pro adds 👀 > Multi-speaker dialogue. > Voice cloning from short reference samples. > MCP plus agent-skill support for teams wiring speech into voice agents and long-form audio.

testingcatalog's profile picture

🚨 AI News | TestingCatalog

71,493 subscribers

333,682 views • 1 month ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Miso One is an open-source voice model built for real-time conversations, responding in about 110 milliseconds while also cloning voices from short audio samples. Its speed makes Al voice chats feel smoother, faster, and much closer to natural human conversation
0:56

Miso One is an open-source voice model built for real-time conversations, responding in about 110 milliseconds while also cloning voices from short audio samples. Its speed makes Al voice chats feel smoother, faster, and much closer to natural human conversation

Hugging Models

15,754 views • 3 months ago

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.
2:02

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.

PlayAI

105,659 views • 2 years ago

Eleven v3 Conversational, our most expressive model for realtime speech, is now generally available. For developers building voice experiences that respond with real emotion, Eleven v3 Conversational includes audio tags for fine-grained control and support across 70+ languages.
1:21

Eleven v3 Conversational, our most expressive model for realtime speech, is now generally available. For developers building voice experiences that respond with real emotion, Eleven v3 Conversational includes audio tags for fine-grained control and support across 70+ languages.

ElevenLabs

126,444 views • 1 month ago

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.
0:26

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.

Akshay 🚀

468,933 views • 8 months ago

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.
1:33

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.

Sudarshan Kamath

71,298 views • 6 months ago

Introducing Parrot 🦜 Our first speech-to-text model built for production-grade voice agents with an industry leading accuracy, built for noisy calls, regional dialects and compressed audio. Trained on thousands of hours of real-world audio to make sure when you say Udaipur, the agent doesn't hear 'you-die-poor'.
0:45

Introducing Parrot 🦜 Our first speech-to-text model built for production-grade voice agents with an industry leading accuracy, built for noisy calls, regional dialects and compressed audio. Trained on thousands of hours of real-world audio to make sure when you say Udaipur, the agent doesn't hear 'you-die-poor'.

Vedant

15,953 views • 3 months ago

ElevenLabs just lost the crown - to open source. Chatterbox by Resemble AI (I remember writing about this team back in 2022 as a pioneer of AI audio) just released as an open-source alternative for audio generation and voice cloning. - Zero-shot voice cloning from just 5 seconds of audio - Unique emotion intensity control—from subtle to dramatically expressive - Real-time voice synthesis faster than real-time inference - Built-in watermarking for secure, trusted audio - Consistently preferred over ElevenLabs in blind evaluations Fully open-source. No hidden restrictions. This is the way. Check out the demo:
0:26

ElevenLabs just lost the crown - to open source. Chatterbox by Resemble AI (I remember writing about this team back in 2022 as a pioneer of AI audio) just released as an open-source alternative for audio generation and voice cloning. - Zero-shot voice cloning from just 5 seconds of audio - Unique emotion intensity control—from subtle to dramatically expressive - Real-time voice synthesis faster than real-time inference - Built-in watermarking for secure, trusted audio - Consistently preferred over ElevenLabs in blind evaluations Fully open-source. No hidden restrictions. This is the way. Check out the demo:

AI Breakfast

454,451 views • 1 year ago

Wow! New Speech to Speech model - Fish Agent v0.1 3B by Fish Audio 🔥 > Trained on 700K hours of multilingual audio > Continue-pretrained version of Qwen-2.5-3B-Instruct for 200B audio & text tokens > Zero-shot voice cloning > Text + audio input/ Audio output > Ultra-fast inference w/ 200ms TTFA > Models on the Hub & Finetuning code on its way! 🚀 What an amazing time to be alive 🤗
1:08

Wow! New Speech to Speech model - Fish Agent v0.1 3B by Fish Audio 🔥 > Trained on 700K hours of multilingual audio > Continue-pretrained version of Qwen-2.5-3B-Instruct for 200B audio & text tokens > Zero-shot voice cloning > Text + audio input/ Audio output > Ultra-fast inference w/ 200ms TTFA > Models on the Hub & Finetuning code on its way! 🚀 What an amazing time to be alive 🤗

Vaibhav (VB) Srivastav

67,003 views • 1 year ago

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗
2:10

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

Vaibhav (VB) Srivastav

79,645 views • 1 year ago

🚨 THIS IS INSANE A developer has released a free AI voice studio capable of cloning almost any voice in just a few seconds. It's called Voicebox. And it has already surpassed 50,500 stars on GitHub. Here's how it works: 1.- Upload a short audio sample and clone a voice in seconds. 2.- Generate speech in 23 different languages using multiple TTS engines. 3.- Run everything locally for greater privacy, and you can integrate it into your own applications. It also includes voice dictation, support for AI agents, and MCP integration. All in a single open-source tool. Save this tool. I've left the link in the next comment 👇
0:22

🚨 THIS IS INSANE A developer has released a free AI voice studio capable of cloning almost any voice in just a few seconds. It's called Voicebox. And it has already surpassed 50,500 stars on GitHub. Here's how it works: 1.- Upload a short audio sample and clone a voice in seconds. 2.- Generate speech in 23 different languages using multiple TTS engines. 3.- Run everything locally for greater privacy, and you can integrate it into your own applications. It also includes voice dictation, support for AI agents, and MCP integration. All in a single open-source tool. Save this tool. I've left the link in the next comment 👇

Nova

26,530 views • 1 month ago

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗
1:21

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗

Vaibhav (VB) Srivastav

299,066 views • 1 year ago

VoxCPM 2 just dropped by OpenBMB Only 2B-param open-source TTS (Text-to-Speech) model built for production-grade multilingual voice work. Apache-2.0 license, Can run on only 8GB VRAM. • Eliminates the "robotic" feel of traditional TTS, delivering prosody and emotional depth suitable for high-stakes professional environments like filmmaking, gaming, animation, and audiobooks. • 30-language multilingual: no language tag needed, just type in a supported language and generate directly. • Voice design: create a brand-new voice from a text description alone, like age, tone, pace, or emotion. No reference audio required. Describe the desired voice characteristics (gender, age, tone, emotion, pace …) in Control Instruction, and VoxCPM2 will craft a unique voice from your description alone. • Controllable cloning: clone from a short clip, then steer delivery style without losing the speaker’s core voice. • Ultimate cloning: use reference audio + transcript for continuation-style cloning that keeps the tiny vocal details. • 48kHz output: takes 16kHz reference audio and produces studio-quality speech without an external upsampler. • Real-time ready: around 0.3 RTF on RTX 4090, even lower with Nano-VLLM. • Commercial use: Apache-2.0 licensed. Developer-Friendly Infrastructure: - Native Torch Inference: Direct support for PyTorch-based workflows. - Training Flexibility: Supports both full-parameter and LoRA fine-tuning for specific domain adaptation. - Production Readiness: Compatible with voxcpm-nanovllm for large-scale, high-concurrency deployment.
1:58

VoxCPM 2 just dropped by OpenBMB Only 2B-param open-source TTS (Text-to-Speech) model built for production-grade multilingual voice work. Apache-2.0 license, Can run on only 8GB VRAM. • Eliminates the "robotic" feel of traditional TTS, delivering prosody and emotional depth suitable for high-stakes professional environments like filmmaking, gaming, animation, and audiobooks. • 30-language multilingual: no language tag needed, just type in a supported language and generate directly. • Voice design: create a brand-new voice from a text description alone, like age, tone, pace, or emotion. No reference audio required. Describe the desired voice characteristics (gender, age, tone, emotion, pace …) in Control Instruction, and VoxCPM2 will craft a unique voice from your description alone. • Controllable cloning: clone from a short clip, then steer delivery style without losing the speaker’s core voice. • Ultimate cloning: use reference audio + transcript for continuation-style cloning that keeps the tiny vocal details. • 48kHz output: takes 16kHz reference audio and produces studio-quality speech without an external upsampler. • Real-time ready: around 0.3 RTF on RTX 4090, even lower with Nano-VLLM. • Commercial use: Apache-2.0 licensed. Developer-Friendly Infrastructure: - Native Torch Inference: Direct support for PyTorch-based workflows. - Training Flexibility: Supports both full-parameter and LoRA fine-tuning for specific domain adaptation. - Production Readiness: Compatible with voxcpm-nanovllm for large-scale, high-concurrency deployment.

Rohan Paul

13,541 views • 5 months ago

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?
3:29

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?

Melvin Vivas

27,722 views • 1 year ago

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:
2:41

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:

Andrew Ng

87,868 views • 1 year ago

Learn to build your own voice-activated AI assistant that can execute tasks like gathering recent AI news from the web, scripting out a podcast, and using tools to put all that into a multi-speaker podcast. See our new short course: "Building Live Voice Agents with Google’s ADK (Agent Development Kit),” taught by Google’s Lavi Nigam and Sita Lakshmi Sangameswaran. ADK provides modular components that make it easy to build and debug agents. It also includes a built-in web interface for tracing agentic reasoning. This course illustrates these concepts via building a live voice agent that can chain actions to complete a complex task like creating a podcast. This requires maintaining context, implementing guardrails, reasoning, and handling audio streaming, while keeping latency low. You’ll learn to: - Build voice agents that listen, reason, and respond - Guide your agent to follow a specific workflow to accomplish a task - Coordinate specialized agents to build an agentic podcast workflow that researches topics and produces multi-speaker audio - Understand how to deploy an agent into production Even if you’re not yet building voice systems, you'll find understanding how realtime agents stream data and maintain reliability useful for designing modern agentic applications. Please join here:
2:12

Learn to build your own voice-activated AI assistant that can execute tasks like gathering recent AI news from the web, scripting out a podcast, and using tools to put all that into a multi-speaker podcast. See our new short course: "Building Live Voice Agents with Google’s ADK (Agent Development Kit),” taught by Google’s Lavi Nigam and Sita Lakshmi Sangameswaran. ADK provides modular components that make it easy to build and debug agents. It also includes a built-in web interface for tracing agentic reasoning. This course illustrates these concepts via building a live voice agent that can chain actions to complete a complex task like creating a podcast. This requires maintaining context, implementing guardrails, reasoning, and handling audio streaming, while keeping latency low. You’ll learn to: - Build voice agents that listen, reason, and respond - Guide your agent to follow a specific workflow to accomplish a task - Coordinate specialized agents to build an agentic podcast workflow that researches topics and produces multi-speaker audio - Understand how to deploy an agent into production Even if you’re not yet building voice systems, you'll find understanding how realtime agents stream data and maintain reliability useful for designing modern agentic applications. Please join here:

Andrew Ng

118,297 views • 11 months ago

Voxtral TTS is built for global applications supporting 9 languages and powering voice workflows. ✅ Full audio intelligence: Works with Voxtral Transcribe for end-to-end speech-to-speech, or plugs into any STT + LLM stack. ✅ Built for business: From customer support to real-time translation, it’s the output layer that passes the human test. 🎥 See it in action:
1:27

Voxtral TTS is built for global applications supporting 9 languages and powering voice workflows. ✅ Full audio intelligence: Works with Voxtral Transcribe for end-to-end speech-to-speech, or plugs into any STT + LLM stack. ✅ Built for business: From customer support to real-time translation, it’s the output layer that passes the human test. 🎥 See it in action:

Mistral AI

28,284 views • 6 months ago

Most AI agents stop at chat. Agent Max is built for what comes after. Max tools. Max control and configurability. Max production readiness. Your agent can use: • any tools, APIs, MCP, and workflows • built-in knowledge: docs/website • multi-model: OpenAI, Claude, Gemini... • agent-to-agent handoffs • human-in-the-loop • logs, usage tracking, environments, and RBAC • enterprise controls for SOC2/GDPR/HIPAA/ISO needs • hosted chat UI, API, Skill in agents, Slack, WhatsApp, Teams, Voice, and more Agent Max is live now in BuildShip for everyone. Give it a try, or comment/DM to book a demo if you want help setting up your first agent.
1:15

Most AI agents stop at chat. Agent Max is built for what comes after. Max tools. Max control and configurability. Max production readiness. Your agent can use: • any tools, APIs, MCP, and workflows • built-in knowledge: docs/website • multi-model: OpenAI, Claude, Gemini... • agent-to-agent handoffs • human-in-the-loop • logs, usage tracking, environments, and RBAC • enterprise controls for SOC2/GDPR/HIPAA/ISO needs • hosted chat UI, API, Skill in agents, Slack, WhatsApp, Teams, Voice, and more Agent Max is live now in BuildShip for everyone. Give it a try, or comment/DM to book a demo if you want help setting up your first agent.

BuildShip

75,946 views • 3 months ago

Introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions! 💬 Available for both real-time speech and audio file transcription, with support for: 💡 smart transcription: rewrite and format text based on intent. 🌍 support for 85+ languages, regional accents and diverse dialects. 📚 custom vocabulary: recognize jargon and specific spellings. 💯 high precision in alphanumerics. 🫂 multi-speaker identification.
4:49

Introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions! 💬 Available for both real-time speech and audio file transcription, with support for: 💡 smart transcription: rewrite and format text based on intent. 🌍 support for 85+ languages, regional accents and diverse dialects. 📚 custom vocabulary: recognize jargon and specific spellings. 💯 high precision in alphanumerics. 🫂 multi-speaker identification.

Thor 雷神 ⚡️

22,961 views • 27 days ago

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)
0:30

Build a real-time AI Voice Agent that can actually sell. In less than 30 minutes, you'll learn how to build a sophisticated real-time voice sales agent that can have natural conversations with potential customers. Includes a full code notebook, recorded tutorial, and docs The stack: ⚡ fast inference 🎙 LiveKit for real-time audio/video infrastructure 🗣 realistic speech synthesis (STT/TTS)

Sarah Chieng

452,438 views • 1 year ago

The voice-to-voice AI Pareto frontier. (You'll never believe this one weird trick ...) If you're building conversational voice AI apps, you care a lot about: ➟ Latency ➟ Cost ➟ LLM response quality (predictable behavior, coverage of the full surface area of your needs, reliable function calling, "reasoning") ➟ Voice quality (correct pronunciations, consistent tone, appropriate affect, steerability, "human-ness") AI model performance is a jagged frontier and has been moving fast for all of 2024. This is especially true for conversational voice, because you're usually using several models in combination. LLMs with native audio capabilities are the newest evolution pushing the performance frontier. Here's a multi-lingual voice conversation using Gemini Flash 1.5's native audio input. But there's a problem ...
1:01

The voice-to-voice AI Pareto frontier. (You'll never believe this one weird trick ...) If you're building conversational voice AI apps, you care a lot about: ➟ Latency ➟ Cost ➟ LLM response quality (predictable behavior, coverage of the full surface area of your needs, reliable function calling, "reasoning") ➟ Voice quality (correct pronunciations, consistent tone, appropriate affect, steerability, "human-ness") AI model performance is a jagged frontier and has been moving fast for all of 2024. This is especially true for conversational voice, because you're usually using several models in combination. LLMs with native audio capabilities are the newest evolution pushing the performance frontier. Here's a multi-lingual voice conversation using Gemini Flash 1.5's native audio input. But there's a problem ...

kwindla

23,592 views • 1 year ago