Saaras-V4

Sarvam AI released Saaras V4, an automatic speech recognition model pairing an audio encoder with a 3B hybrid state-space LLM decoder trained from scratch in-house, which the company says achieves state-of-the-art performance on all 22 Indian languages and the lowest average word error rate across seven English benchmarks. Saaras V4 supports five transcript formats — transcribe, translate, verbatim, translit, and codemix — and reports a 2.9% language-identification error rate across the top ten Indian languages and 5.22% across all 22. Evaluation used HuggingFace's Open ASR Leaderboard datasets and code plus AI4Bharat's Svarah and Vistaar benchmarks, with results reported in both WER and LLM-WER.

Introducing Saaras V4 The Next Leap in ASR for a Multilingual World We are releasing Saaras V4, the latest generation of our speech recognition model. This post covers the work behind Saaras V4, including the data used to train it, our pre-training approach, the architectural and decoding changes that support multiple output modes, and the evaluation methodology behind our results. We also report benchmark performance across Indian languages, English, and challenging real-world speech conditions. Highlights - Saaras V4 uses an audio encoder, and an LLM decoder. The LLM decoder is a 3B hybrid state space model completely trained from scratch in-house - Saaras V4 achieved SOTA performance on all 22 Indian languages and reaffirms our commitment to even the most low-resource Indian languages - Saaras V4 achieves lowest WER on seven global English datasets, six being foreign English dialects and one being Indian English - You can choose the format that works best for you: Saaras V4 supports five transcript formats: transcribe, translate, verbatim, translit, and codemix - Saaras V4 is robust to noisy audios and code mixing. It also handles dialectical variation seamlessly - Its language identification is also best-in-class: a 2.9% error rate across the top ten Indian languages, and 5.22% across all 22 Inside Saaras V4 Saaras V4 pairs an audio encoder with a 3B hybrid state-space language model that we trained from scratch in-house. We designed the system to handle the range of speech we see in practice, including code-mixing, dialectal variation, and noisy audio, while supporting five different ways of representing the same speech: verbatim transcription, normalized text, code-mixed text, transliteration, and translation. Performance across English benchmarks We evaluated Saaras V4 across seven English speech recognition benchmarks covering Indian English, international accents, meetings, media, finance, and other real-world speech settings. Across these datasets, Saaras V4 achieves the lowest average word error rate. Meeting rooms, far-field microphones Podcast, audiobook, web video Read speech, studio conditions Read speech, harder acoustics Earning calls, financial vocabulary European Parliament speeches Indian-accented English Evaluation methodology - Six international: taken as published at HuggingFace's Open ASR Leaderboard https://huggingface.co/datasets/hf-audio/open-asr-leaderboard - One Indian accented English: Svarah https://huggingface.co/datasets/ai4bharat/Svarah published by AI4Bharat - Normalization and scoring follow the Open ASR Leaderboard's code https://github.com/huggingface/open asr leaderboard Indic Benchmarks for Saaras V4: Vistaar We evaluate Saaras V4 on Vistaar https://github.com/AI4Bharat/vistaar across ten Indian languages and report both standard Word Error Rate WER and LLM-WER. WER remains the standard deterministic measure for speech recognition, counting substitutions, deletions, and insertions between the reference and predicted transcript. In Indic-language settings, however, some of these differences can be orthographic or formatting variations that do not materially change the spoken content. To account for this, we also report LLM-WER https://www.sarvam.ai/blogs/evaluating-indian-language-asr , which adds a semantic adjudication step to determine whether a mismatch changes the meaning of the transcript or simply represents the same content differently. The two metrics are therefore complementary. WER provides a reproducible baseline, while LLM-WER gives a more faithful view of errors that affect the underlying speech content. Detailed breakdown of various benchmarks: Benchmark WER by dataset Lower is better Contains crowd-sourced read speech from the Mozilla Foundation's Commonvoice. Five Modes, One Model Different applications need different representations of the same speech. A compliance archive may need a verbatim transcript, while a CRM workflow may require normalized text and an analytics system may need an English translation. These transformations are often handled through separate post-processing steps, which add complexity and can introduce additional errors. Saaras V4 handles these requirements within the model itself. From the same audio input, it can produce five transcript modes: verbatim, normalized, code-mixed, transliterated, and translated. punctuation restored in English English script translation as spoken - Verbatim: The exact transcription in the native script of the spoken language - Transcribe: The exact transcription in the native script of the spoken language with numbers and dates normalised - Codemix: Transcribe mode plus keeps native english words in english to improve legibility - Translit: Does transcription but in english script. Colloquially referred to as “WhatsApp language” - Translate: The English translation of the audio with numbers normalized Because all five come from one model, there are no extra pre-processing steps that could lead to cascading of errors. Beyond the transcription a. Best in class Language Identification Saaras V4 can identify the spoken language directly from the audio and transcribe it in the corresponding native script, without requiring the language to be specified in advance. On verified IndicVoices utterances, language identification error is 5.22% across all 22 Indian languages, falling to 2.9% across the ten most widely spoken languages. b. Keyterm prompting Keyterm prompting lets you bias transcription toward words or phrases that are easy to miss, such as product names, people’s names, acronyms, or domain-specific terminology. Validated as best on ai4bharat/IndicContextEval https://huggingface.co/datasets/ai4bharat/IndicContextEval Interspeech 2026 : Saaras V4 reaches the lowest WER of 16.03% in the L5 keyword prompting setting, where the domain-entity list is provided in native script along with the language. For dataset details and competitor scores, see the paper https://arxiv.org/pdf/2606.19157 . ઢૂન માટે આંખનું કામ કરે છે અને દરેક વખતે ડ્રોન માટે આંખનું કામ કરે છે અને દરેક વખતે Reference keywords provided 24 c. Built For Real-World Audio Field audio is compressed, clipped, and full of interference. These are conditions where systems trained on clean benchmarks often fall apart. Saaras V4 is designed to remain reliable under these conditions, including noisy audio, code-mixing, and dialectal variation. | Language | Condition | Format | Transcript | |---|---|---|---| | Hindi | Constant wind noise | Verbatim | ए एक बात सुनो ना मैडम दो दो दो दो दो दोनों मिलाकर | | Hindi | Distortion and clipping | Transcribe | सर आपको अपनी पॉलिसी के बारे में कुछ पूछना है? मैं आपसे ये पूछ रही थी कि। | | Hindi | Constant background | Codemix | होते हो। Nice to meet you brothers. Okay. Thank you. Bye. कुछ कुछ price तो ऐसा है कि जो | | Bengali | Heavy traffic | Translit | Maane ami ekta TV kinechilam ami ekta TV installmente niyechilam apnader bank hoyto erokom taka kate okhan theke ki koreche | | Kannada | Static noise | Translate | First, in our art, in our culture, first we built a temple. We used to live in huts. We built big, big temples. If you see it, it's a surprise even now. How they must have built it, for a thousand years, for two thousand years, this kind of thing, it's a surprise. | | English | Channel distortion | Transcribe | Oh, what a record to read What a picture to gaze upon How awful the fact | d. Low-latency streaming For real-time voice applications, latency is as important as transcription quality. Saaras V4 supports streaming with time to first token below 150 ms, allowing downstream systems to begin responding with minimal delay and enabling more natural turn-taking. It also handles long-form audio natively, with multi-minute recordings processed within a second. Integrating Saaras V4 into your platform Integrate Saaras v4 into your application with a simple API key from the Sarvam AI dashboard https://indus.sarvam.ai/ Choose Your Integration Path: - REST API https://docs.sarvam.ai/api/api-guides-tutorials/speech-to-text/rest-api : Synchronous transcription for audio under 30 seconds - Batch API https://docs.sarvam.ai/api/api-guides-tutorials/speech-to-text/batch-api : Asynchronous processing for files up to 2 hours. Speaker Diarization can be enabled in batch mode - WebSocket Real-time https://docs.sarvam.ai/api/api-guides-tutorials/speech-to-text/realtime-streaming : Streaming transcription with partial results for live applications SDKs & Frameworks: Ready-to-use SDKs for Python 3.9+ and Node.js 18+. Framework integrations available for Vercel AI SDK https://docs.sarvam.ai/api/integration/vercel-ai-sdk , LiveKit Agents https://docs.livekit.io/agents/models/stt/sarvam/ and Pipecat Agents https://docs.pipecat.ai/api-reference/server/services/stt/sarvam Output Modes: Configure transcription output: transcribe default , translate to English , translit romanized , or verbatim or codemix Quick Start: See the Developer Quickstart https://docs.sarvam.ai/api/api-guides-tutorials/speech-to-text/rest-api for code examples and authentication details One model across languages With Saaras V4, you no longer have to trade off English performance against Indic language coverage. It delivers strong performance across both, while supporting low-latency streaming and reliable production workloads. This makes it possible to build multilingual voice applications with one ASR model. Curious what else we're building? Explore our APIs and start creating. Curious what else we're building? Explore our APIs and start creating.