正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing Saaras V4, our most capable speech to text model yet. It delivers strong performance across both English and Indian languages, with better accuracy over a much wider range of speech. Saaras V4 was built with specific attention to noise, accents, dialects and mixed-language speech. Read more in the blog:

Sarvam

85,341 subscribers

44,151 次观看 • 3 天前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

30 条评论

Sarvam 的头像

Sarvam3 天前

Saaras V4 is state of the art across all 22 Indian languages. 10 of these languages have no commercial alternative today.

Sarvam 的头像

Sarvam3 天前

It also gets the lowest average word error rate across seven English benchmarks covering global accents, meetings, media and financial audio.

Sarvam 的头像

Sarvam3 天前

Keyterm prompting is a new addition in Saaras V4, giving the model more context before transcription begins. Names, brands, product terms and specialised vocabulary can be provided as context, helping Saaras V4 recognise words that are uncommon, domain-specific or easy to mishear. This is especially useful in areas where a small transcription error can materially change the meaning.

Sarvam 的头像

Sarvam3 天前

Saaras V4 preserves transcription accuracy across noisy audio. We evaluated Saaras V4 on Kathbath Noisy using LLM-WER, across speech affected by compression, clipping and background interference. Saaras V4 maintains substantially higher transcription accuracy under these conditions, with an error rate less than half that of Deepgram Nova-3 and GPT-4o Transcribe.

Sarvam 的头像

Sarvam3 天前

Saaras V4 also supports five transcript formats for different applications. The formats let the same model serve very different workflows, from low-latency voice agents to verbatim transcripts for compliance and cleaner English for analysis.

Vishal Singh 🥑 的头像

Vishal Singh 🥑3 天前

What can Saaras V4 do now that it couldn't before? - Assamese helplines for Assam citizen services, disaster alerts, and health queries - Bodo helplines and panchayat bots for Bodoland / Assam local governance - Manipuri (Meitei) helplines for Manipur public services, hospitals, and education support - Combined Northeast voice desk covering Assamese + Bodo + Manipuri on one line - Santali tribal welfare apps in Jharkhand, Odisha, and Bengal - Santali mining / factory safety voice reporting in Jharkhand and nearby belts - Kashmiri citizen-service IVR and grievance bots for J&K - Dogri citizen-service IVR and local-body helpdesks for Jammu - Maithili agri advisories for Bihar / Mithila farmers - Maithili panchayat and ration / scheme query bots in north Bihar - Konkani banking IVR for Goa and the Konkan coast - Konkani insurance, UPI, and loan collections calls in Goa / coastal Karnataka / Maharashtra - Sanskrit temple recitation transcription and archive search Sanskrit education apps for pathshalas, universities, and exam practice - Sindhi community service, banking, and diaspora support lines - Nepali citizen and tourism helpdesks in Sikkim, Darjeeling, and border districts - Assamese + Nepali thinner-coverage upgrade for state portals that previously failed on dialect and code-mix - Low-resource language voice surveys for elections, health camps, and welfare schemes - Court / police verbatim records in Kashmiri, Dogri, Maithili, Santali, Bodo, or Manipuri - School and literacy apps that accept spoken answers in these languages instead of only Hindi or English Excited to see the ground level impact 🙌

Mayur chaudhary 的头像

Mayur chaudhary3 天前

And what about 1 trillion parameter model ??

sai santosh kumar 的头像

sai santosh kumar3 天前

Still no word level time stamps ?

alt 的头像

alt3 天前

Any chance of speech to speech model in near future?

Aware Citizen 的头像

Aware Citizen3 天前

Woh great going team Sarvam india needs this due to various languages spoken in pan india..this will revolutionize translation in future

Lovey Jain 的头像

Lovey Jain3 天前

Building on side Prem — a space where people can talk to someone they love/lost by uploading their voice audio and having an AI-powered conversation. I’m exploring whether Sarvam AI can help with the voice cloning + speech-to-speech pipeline Which Sarvam model/process would do?

✦ SK ✦ 的头像

✦ SK ✦3 天前

sab kuch bna diya text SOTA model kab laoge?? Jo modi ke vishwaguru ka sapna kab pura kroge?? AGI???

Assu_Bhadhu 的头像

Assu_Bhadhu3 天前

open weight?

Oleks 的头像

Oleks3 天前

noise and accents are where most speech models fall apart

MochiBro 的头像

MochiBro3 天前

just wow 😲😳

Mesut De 的头像

Mesut De3 天前

conrat

Xien Luis 的头像

Xien Luis3 天前

bulbul v4 next, trust

Tree (🌸, 🌿) 的头像

Tree (🌸, 🌿)3 天前

gov's propaganda mouthpiece ai model...

LastResort 的头像

LastResort3 天前

@grok price of this one?

Shrestha 的头像

Shrestha3 天前

What about coding agents? Yet on Waitlist🙁

Rajat 的头像

Rajat3 天前

new Saaras V4 model is already available on Vercel's @aisdk ❤️

Democracy 的头像

Democracy3 天前

Any Plan Coding Models ?

Vince Dsouza 的头像

Vince Dsouza3 天前

the gradients and fonts on this are so clean!!!

On-Device Logs 的头像

On-Device Logs3 天前

bruh another s2t model? hope it actually outperforms the hype

ankan 的头像

ankan3 天前

Hey is anybody building with Sarvam please connect, have questions 🫵🏻

Sahil Nawaz 的头像

Sahil Nawaz3 天前

Congratulations on the launch!! Let's build a community together! DMs are open!

Audemy 的头像

Audemy3 天前

kathbath, the noise benchmark, is read speech: a sample passed only if it exactly matched the prompt, and speakers were told to skip words they found hard to pronounce. that covers accent and channel. disordered speech is a different axis, and it's where asr is access.

Isoldegwow 的头像

Isoldegwow3 天前

Finally a benchmark for people who start a sentence in English and finish it in Hindi.

Anil Pai 的头像

Anil Pai3 天前

Its v4 and still no word level timestamps. What is the use of segment level timestamps ? 🤷

Evia AI 的头像

Evia AI3 天前

This kind of robustness to accents and noise is what really makes STT usable in real world

相关视频

Introducing Saaras V4 Multi-speaker Our best-in-class speech recognition model that accurately captures overlapping conversations and multi-speaker interactions, while delivering state-of-the-art performance in English across accents.

Introducing Saaras V4 Multi-speaker Our best-in-class speech recognition model that accurately captures overlapping conversations and multi-speaker interactions, while delivering state-of-the-art performance in English across accents.

Sarvam

31,374 次观看 • 2 个月前

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.

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 次观看 • 1 个月前

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:

AI4Bharat

28,681 次观看 • 1 年前

Introducing the open-source Next.js Audio Starter Kit Add Text to Speech, Speech to Text, Sound Effects and Conversational AI to your product in minutes. Built with: • ElevenLabs SDK • Next.js + shadcn/ui • Tailwind CSS v4 Repo link in the comments below:

Introducing the open-source Next.js Audio Starter Kit Add Text to Speech, Speech to Text, Sound Effects and Conversational AI to your product in minutes. Built with: • ElevenLabs SDK • Next.js + shadcn/ui • Tailwind CSS v4 Repo link in the comments below:

ElevenLabs Developers

145,836 次观看 • 1 年前

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing.

Introducing Scribe — the most accurate Speech to Text model. It has the highest accuracy on benchmarks, outperforming previous state-of-the-art models such as Gemini 2.0 and OpenAI Whisper v3. It’s now the leading model for English, Spanish, Italian, and many more. With support for 99 languages, speaker diarization, character-level timestamps, and non-speech events such as laughing.

ElevenLabs

465,139 次观看 • 1 年前

introducing Gemini 3.5 Transcribe: our most precise speech-to-text model yet, designed for intelligent voice interactions this new model: - seamlessly handles self-corrections - removes filler words to deliver clean, formatted text - understands your natural intent and speaking style - captures audio, even in noisy environments - supports 85+ languages, including regional accents and diverse dialects try it today in the Gemini API and in AI Studio

introducing Gemini 3.5 Transcribe: our most precise speech-to-text model yet, designed for intelligent voice interactions this new model: - seamlessly handles self-corrections - removes filler words to deliver clean, formatted text - understands your natural intent and speaking style - captures audio, even in noisy environments - supports 85+ languages, including regional accents and diverse dialects try it today in the Gemini API and in AI Studio

Google AI Studio

238,290 次观看 • 1 个月前

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 次观看 • 3 年前

Introducing Eleven Multilingual v2: our new AI speech model supporting 28 languages! v2 comes with enhanced conversational capability, higher output quality & the ability to better preserve unique voice characteristics across languages. Read more:

Introducing Eleven Multilingual v2: our new AI speech model supporting 28 languages! v2 comes with enhanced conversational capability, higher output quality & the ability to better preserve unique voice characteristics across languages. Read more:

ElevenLabs

293,463 次观看 • 3 年前

Introducing Qwen3-TTS! 🗣️ Our new text-to-speech model is designed to be multi-timbre, multi-lingual, and multi-dialect for natural, expressive audio. It delivers strong performance in English & Chinese, and we're excited for you to hear it for yourself!

Introducing Qwen3-TTS! 🗣️ Our new text-to-speech model is designed to be multi-timbre, multi-lingual, and multi-dialect for natural, expressive audio. It delivers strong performance in English & Chinese, and we're excited for you to hear it for yourself!

Tongyi Lab

1,015,006 次观看 • 1 年前

Today, we’re introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions in Google Antigravity. It pairs screen context and chat history, with your permission, to ensure pinpoint transcription accuracy across file names, agent thoughts, and active documents.

Today, we’re introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions in Google Antigravity. It pairs screen context and chat history, with your permission, to ensure pinpoint transcription accuracy across file names, agent thoughts, and active documents.

Google Antigravity

142,687 次观看 • 1 个月前

Our new Speech-to-Text model can handle far-field mics and soft speakers with more accuracy. It normalises gain as the stream arrives, so someone who leans away or speaks from across a meeting room stays in range. Try it at

Our new Speech-to-Text model can handle far-field mics and soft speakers with more accuracy. It normalises gain as the stream arrives, so someone who leans away or speaks from across a meeting room stays in range. Try it at

Gradium

13,849 次观看 • 1 个月前

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'.

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 次观看 • 4 个月前

Introducing Scribe v2 Realtime – the most accurate real-time Speech to Text model. Built for voice agents, meeting notetakers, and live applications, it transcribes in 150ms across 90+ languages, including English, French, German, Italian, Spanish, Portuguese, Hindi, and Japanese. Available today by API and through ElevenLabs Agents.

Introducing Scribe v2 Realtime – the most accurate real-time Speech to Text model. Built for voice agents, meeting notetakers, and live applications, it transcribes in 150ms across 90+ languages, including English, French, German, Italian, Spanish, Portuguese, Hindi, and Japanese. Available today by API and through ElevenLabs Agents.

ElevenLabs

318,433 次观看 • 10 个月前

We have officially launched Fun-ASR1.5, a major update to our end-to-end speech recognition model. This release focuses on three core pillars: broader language coverage, language switching, and production-ready text output. Key Features: • Multilingual Support: Supports high-accuracy recognition for 30 languages across Asia, Europe, and the Middle East within a single model. • Language Switching: Handles mixed-language speech (Code-Switching) natively, automatically detecting and transcribing language shifts without the need for manual tagging. • Professional Text Output: Delivers "ready-to-use" text with smart punctuation and automatic formatting for dates, numbers, and currencies. Fun-ASR1.5 bridges the gap between raw audio and professional documentation, providing a reliable engine for global communication.

We have officially launched Fun-ASR1.5, a major update to our end-to-end speech recognition model. This release focuses on three core pillars: broader language coverage, language switching, and production-ready text output. Key Features: • Multilingual Support: Supports high-accuracy recognition for 30 languages across Asia, Europe, and the Middle East within a single model. • Language Switching: Handles mixed-language speech (Code-Switching) natively, automatically detecting and transcribing language shifts without the need for manual tagging. • Professional Text Output: Delivers "ready-to-use" text with smart punctuation and automatic formatting for dates, numbers, and currencies. Fun-ASR1.5 bridges the gap between raw audio and professional documentation, providing a reliable engine for global communication.

Tongyi Lab

3,917,307 次观看 • 5 个月前

What if voice AI could understand context, intent, and emotion — not just words? 🎙️ Meet Seed Speech 2.0. A new speech AI stack designed for natural, expressive conversations — with major upgrades in both text-to-speech (TTS) and speech recognition (ASR). Built for developers and creators who want natural conversational speech. What’s inside: - Natural and expressive speech generation - Prompt-controlled emotion and tone - High-accuracy multilingual recognition - Strong contextual reasoning Built for: 🎧 Voice content creation 🤖 AI assistants ☎️ Customer service 🎬 Dubbing & subtitling 📊 Audio-video analysis Voice AI built for expression, accuracy, and understanding. Try it now → Read more about Seed Speech here → #SeedSpeech #VoiceAI #SpeechAI #AI

What if voice AI could understand context, intent, and emotion — not just words? 🎙️ Meet Seed Speech 2.0. A new speech AI stack designed for natural, expressive conversations — with major upgrades in both text-to-speech (TTS) and speech recognition (ASR). Built for developers and creators who want natural conversational speech. What’s inside: - Natural and expressive speech generation - Prompt-controlled emotion and tone - High-accuracy multilingual recognition - Strong contextual reasoning Built for: 🎧 Voice content creation 🤖 AI assistants ☎️ Customer service 🎬 Dubbing & subtitling 📊 Audio-video analysis Voice AI built for expression, accuracy, and understanding. Try it now → Read more about Seed Speech here → #SeedSpeech #VoiceAI #SpeechAI #AI

BytePlus

19,840 次观看 • 6 个月前

We're introducing two new transcription models in the API: • GPT-Live-Transcribe: built for low-latency live transcription. • GPT-Transcribe: optimized for asynchronous transcription of completed audio files and batch workloads. Both models better understand context and deliver more accurate transcription on real world audio across accents and languages, including for short phrases, numbers, specialized terminology, and speech with loud background noise.

We're introducing two new transcription models in the API: • GPT-Live-Transcribe: built for low-latency live transcription. • GPT-Transcribe: optimized for asynchronous transcription of completed audio files and batch workloads. Both models better understand context and deliver more accurate transcription on real world audio across accents and languages, including for short phrases, numbers, specialized terminology, and speech with loud background noise.

OpenAI Developers

454,993 次观看 • 2 个月前

Universal-Streaming is our real-time speech-to-text model — built for voice agents with ~300ms latency, high accuracy, unlimited concurrency, and just $0.15/hour. 👉 Test it live in the playground →

Universal-Streaming is our real-time speech-to-text model — built for voice agents with ~300ms latency, high accuracy, unlimited concurrency, and just $0.15/hour. 👉 Test it live in the playground →

AssemblyAI

1,017,880 次观看 • 1 年前

Speech to Speech is now available in 29 languages. In November, we launched Speech to Speech, enabling you to transform your voice into another character with full control over emotions, timing, and delivery. Today we're making Speech to Speech multilingual. Use Speech to Speech to get more control than with prompting alone. Simply say it how you want it, choose a target voice, and generate.

Speech to Speech is now available in 29 languages. In November, we launched Speech to Speech, enabling you to transform your voice into another character with full control over emotions, timing, and delivery. Today we're making Speech to Speech multilingual. Use Speech to Speech to get more control than with prompting alone. Simply say it how you want it, choose a target voice, and generate.

ElevenLabs

113,343 次观看 • 2 年前

Drop 5/14: Introducing Bulbul V3, our latest text-to-speech model. It raises the bar for how human it sounds, while being super robust. In an independent third-party human listening study, Bulbul V3 delivers the highest listener preference, and low error rates across use-cases and languages. See details in our blog, but first watch the video.

Drop 5/14: Introducing Bulbul V3, our latest text-to-speech model. It raises the bar for how human it sounds, while being super robust. In an independent third-party human listening study, Bulbul V3 delivers the highest listener preference, and low error rates across use-cases and languages. See details in our blog, but first watch the video.

Pratyush Kumar

424,383 次观看 • 7 个月前

We are launching the Eleven v3 (alpha) API. Built for async use cases, Eleven v3 (alpha) delivers the most expressive Text to Speech model: - Dialogue mode, unlimited amount of speakers - 70+ languages - Enhanced voice and emotional control with [audio tags]

We are launching the Eleven v3 (alpha) API. Built for async use cases, Eleven v3 (alpha) delivers the most expressive Text to Speech model: - Dialogue mode, unlimited amount of speakers - 70+ languages - Enhanced voice and emotional control with [audio tags]

ElevenLabs

8,188,968 次观看 • 1 年前