Close Menu
NCIJ Network NCIJ Network
    What's Hot

    APEC Summit: Chile, Mexico, and Peru Leaders Travel to Shenzhen

    November 20, 2026

    Can the ‘pink salt trick’ help with weight loss?

    November 20, 2026

    Trump China summit with Putin and Xi high on spectacle

    November 20, 2026
    Facebook X (Twitter) Instagram
    Trending
    • APEC Summit: Chile, Mexico, and Peru Leaders Travel to Shenzhen
    • Can the ‘pink salt trick’ help with weight loss?
    • Trump China summit with Putin and Xi high on spectacle
    • Burnham has agreed EU reset deal with tuition fees issue unresolved, says No 10 | Trade policy
    • Mahmood ‘smells a rat’ over housing provision for vulnerable people in Birmingham | Housing
    • A fast-growing heart is good for the Grinch. People are another story
    • Europe sends mixed signals on fossil fuels: Norway’s climate ruling raises the stakes as EU postpones methane rules
    • Milwaukee teen turns TikTok research into a trash bin cleaning business
    • About
      • Our Team
      • Editorial Policy
      • Editorial Independence
      • International Support
    • Trust & Standards
      • AI Usage Policy
      • Conflict of Interest Policy
      • Corrections Policy
      • Ethics Policy
      • Fact-Checking Policy
      • Source Protection
    • Get Involved
      • Guide for Sources
      • Support Independent Journalism
    • Legal
      • Cookie Policy
      • Privacy Policy
      • Terms of Use
    Facebook X (Twitter) Instagram
    NCIJ Network NCIJ Network
    Friday, November 20
    • Home
    • World
    • Ai
    • Business
    • Politics
    • Health
    • Crypto
    • Science
    • Technology
    • Cybersecurity
    • Defense & Security
    • Economy
    • Energy
    • Europe
    • More
      • Fact Check
      • Investigations
      • Opinion & Analysis
      • Environment
    NCIJ Network NCIJ Network
    Home»Artificial Intelligence

    Sarvam AI Releases Saaras V4: A Speech-to-Text Model for All 22 Indian Languages and Global English

    NCIJ NETWNCIJ NETWORKBy NCIJ NETWNCIJ NETWORKSeptember 26, 2026 Artificial Intelligence No Comments5 Mins Read
    Share
    Facebook Twitter LinkedIn Pinterest Email

    Sarvam AI has released Saaras V4, the newest generation of its speech recognition model. It covers all 22 scheduled Indian languages plus English, now including global English accents. Sarvam reports state-of-the-art accuracy across all 22 languages.

    Is it deployable? Yes, through Sarvam’s API today, using model="saaras:v4". Weights are not public, and Sarvam’s SageMaker self-hosting docs currently cover Saaras v3 only.

    What is Inside Saaras V4

    Saaras V4 is an encoder-decoder system. An audio encoder converts the waveform into embeddings that carry phonetic and acoustic detail. A temporal-downsampling adapter then shortens that sequence and projects it into the language model’s embedding space. This keeps long recordings inside the decoder’s context budget.

    The decoder is Sarvam-3B, a 3B-parameter hybrid state-space language model trained from scratch in-house. It reads the audio features alongside a text prompt. It then emits the transcript autoregressively, feeding each token back as input for the next.

    Benchmark Results

    • English: Sarvam evaluated 7 English datasets. Six come from Hugging Face’s Open ASR Leaderboard: AMI, GigaSpeech, LibriSpeech clean, LibriSpeech other, SPGISpeech and VoxPopuli. The seventh is AI4Bharat’s Indian-accented Svarah. Scoring follows the leaderboard’s normalization code. Saaras V4 posts the lowest average WER among the models Sarvam benchmarked.
    • Indic: On Vistaar, Sarvam reports results across 10 Indian languages using both WER and LLM-WER. LLM-WER adds a semantic check. It separates real meaning errors from harmless spelling or formatting variants common in Indic scripts.
    • Noisy audio: On Kathbath Noisy, measured with LLM-WER, Sarvam says Saaras V4’s error rate is under half that of Deepgram Nova-3 and GPT-4o Transcribe. The set includes compressed, clipped and background-heavy recordings.
    • Language ID: On verified IndicVoices utterances, language identification error is 2.9% across the top 10 Indian languages. It is 5.22% across all 22.

    It is important to note that all numbers above are vendor-reported. Independent reproduction has not been published yet.

    5 Output Modes From 1 Model

    The same audio can return 5 representations, selected through the mode parameter:

    • transcribe (default): native script with numbers and dates normalized.
    • verbatim: every word as spoken, fillers and spoken numbers kept.
    • codemix: native script, with English words left in English.
    • translit: the full utterance in Latin script.
    • translate: an English translation with numbers normalized.

    Sarvam’s argument is simple. Handling these inside the model removes post-processing steps that can compound errors.

    Keyterm Prompting

    Keyterm prompting is new in V4 and works only with saaras:v4. You pass a JSON list under keyterms, with up to 50 terms of 64 characters each. Keyterms bias recognition; they do not guarantee output. Use codemix mode when a brand such as PhonePe must stay in Latin script.

    On IndicContextEval (paper, Interspeech 2026), Saaras V4 reports 16.03% WER in the L5 keyword-prompting setting. Sarvam says that is the lowest score on the benchmark.

    Streaming, Long Audio and Pricing

    • Streaming: WebSocket with partial results and time to first token below 150 ms.
    • REST: synchronous transcription for clips up to 30 seconds.
    • Batch: asynchronous jobs up to 2 hours per file, with optional speaker diarization.
    • SDKs: Python 3.9+ and Node.js 18+, plus LiveKit Agents, Pipecat and Vercel AI SDK integrations.
    • Price: Sarvam lists speech-to-text at ₹30 per hour for real-time, streaming and batch, and ₹45 per hour with diarization.

    Saaras v3 stays the default model. V4 uses the same request shape, so switching is a 1-line change.

    English global Indian Languages model Releases Saaras Sarvam SpeechtoText
    NCIJ NETWNCIJ NETWORK
    • Website

    Keep Reading

    Perplexity Launches Orchestrator API for Failover and Model Routing

    Meta FAIR Self-Improving Memory Hits 56.0 on Continual Learning Bench

    13 Best Agent Gateways in 2026 for MCP, A2A and LLM Traffic: Kong, Bifrost, AgentCore, Arcade

    Not If, But How: Responding to Security Incidents in the Age of AI Attackers

    Google DeepMind Releases Gemini 4 Neon: 1M Context, #1 on AA Coding Agent Index

    Nutrient Data Extraction API: JSON Matching Your Schema With Per-Field Citations and Confidence

    Add A Comment
    Leave A Reply Cancel Reply

    Editors Picks

    APEC Summit: Chile, Mexico, and Peru Leaders Travel to Shenzhen

    November 20, 2026

    Can the ‘pink salt trick’ help with weight loss?

    November 20, 2026

    Trump China summit with Putin and Xi high on spectacle

    November 20, 2026

    Burnham has agreed EU reset deal with tuition fees issue unresolved, says No 10 | Trade policy

    November 20, 2026
    Latest Posts

    How ‘gentle power’ can preserve traditional biodiversity in Tokyo

    August 21, 2026

    This weight-loss hormone may protect the liver even without weight loss

    August 21, 2026

    Bitcoin Rally Lifts Crypto Stocks as Canaan Jumps 25%

    August 21, 2026

    Subscribe to News

    Get the latest sports news from NewsSite about world, sports and politics.

    NCIJ Network is an independent digital news platform delivering trusted investigative journalism, European and global news, in-depth analysis, and fact-based reporting with accuracy, transparency, and integrity.

    Facebook X (Twitter) Instagram Pinterest YouTube

    APEC Summit: Chile, Mexico, and Peru Leaders Travel to Shenzhen

    November 20, 2026

    Can the ‘pink salt trick’ help with weight loss?

    November 20, 2026

    Trump China summit with Putin and Xi high on spectacle

    November 20, 2026

    Subscribe to Updates

    Get the latest creative news from FooBar about art, design and business.

    Type above and press Enter to search. Press Esc to cancel.