Sarvam AI Speech to Text
sarvam.ai
Spec sheet
- Product
- Sarvam Speech to Text converts audio into text and offers a free browser playground and an API.Read 8 Oct 2026 · sarvam.ai
- Deployment
- Sarvam says regulated workloads can use VPC or on-premise deployment; its self-hosted guide describes deploying a Saaras model on Amazon SageMaker in the customer’s AWS account and VPC.Read 8 Oct 2026 · docs.sarvam.ai
- Free plan
- NoRead 20 Sep 2026 · sarvam.ai
- Integrations
- Sarvam lists LiveKit, Pipecat, n8n, Vercel AI SDK, and LangChain integrations, plus official Python and JavaScript SDKs.Read 8 Oct 2026 · docs.sarvam.ai
- Security
- Sarvam states API inputs are not used for model training, data is deleted after processing by default, and processing occurs within India without cross-border transfers.Read 8 Oct 2026 · sarvam.ai
- Compliance
- The product page lists SOC 2 Type II, ISO 27001, and DPDP compliance, along with role-based access and audit trails.Read 8 Oct 2026 · sarvam.ai
- Support
- Sarvam’s API documentation lists support by email at [email protected] and a Discord community.Read 8 Oct 2026 · docs.sarvam.ai
- Headquarters
- Bengaluru, Karnataka, IndiaRead 28 Sep 2026 · sarvam.ai
- API access
- YesRead 20 Sep 2026 · sarvam.ai
- API limits
- The REST API handles files under 30 seconds, while Batch handles files up to one hour; Streaming transcribes in real time over WebSocket.Read 8 Oct 2026 · sarvam.ai
- Code-mixing and noise
- Sarvam says Saaras v3 handles mixed-language speech, noisy telephony, and diverse accents, and was trained on over one million hours of real-world audio.Read 8 Oct 2026 · sarvam.ai
- Credits
- The pricing page says signup includes free credits, credits are universal across supported APIs, and unused credits do not expire.Read 8 Oct 2026 · sarvam.ai
- Languages
- Saaras v3 supports all 22 scheduled Indian languages plus English, with automatic language detection.Read 8 Oct 2026 · sarvam.ai
- Languages supported
- 23Read 20 Sep 2026 · sarvam.ai
- Output modes
- The page describes transcribe, translate, transliteration, verbatim, and codemix output modes, with word-level timestamps by default.Read 8 Oct 2026 · sarvam.ai
- Speaker diarization
- The Batch API identifies speakers and tags each word with a stable speaker ID, including for overlapping speech.Read 8 Oct 2026 · sarvam.ai
- Speaker identification
- YesRead 20 Sep 2026 · sarvam.ai
- Streaming
- The product page states sub-150ms time to first token in Fast mode and four streaming modes via WebSocket.Read 8 Oct 2026 · sarvam.ai
- Timestamp support
- YesRead 20 Sep 2026 · sarvam.ai
- Use cases
- The product page names voice agents, post-call analytics, subtitling and captioning, meeting transcription, and voice dictation as use cases.Read 8 Oct 2026 · sarvam.ai
Plans and prices
Real-time ₹30 a month Speech-to-text API Read 20 Sep 2026 · sarvam.ai
Streaming ₹30 a month Streaming speech-to-text Read 20 Sep 2026 · sarvam.ai
Batch ₹30 a month Up to 2 hours per file Read 20 Sep 2026 · sarvam.ai
Batch with diarization ₹45 a month Up to 2 hours per file Read 20 Sep 2026 · sarvam.ai
Enterprise Priced on request Custom pricing for high-volume or production-critical workloads. Custom limits, throughput, pricing, and support · Higher rate limits · Custom concurrency · Volume discounts · Dedicated support and SLAs Read 8 Oct 2026 · sarvam.ai
Starter (Pay as you go) Price not published No monthly commitment; credits can be topped up as needed and never expire. Speech to text: Real-time ₹30.00/hour · Streaming ₹30.00/hour · Batch ₹30.00/hour · Batch with diarization ₹45.00/hour Read 8 Oct 2026 · sarvam.ai
Where Specifiction places it
- AI transcription tools#16 of 468.4
- Transcription tools#16 of 288.2
- Transcription Software#27 of 468.2