Shunya Labs DocsShunya Labs Docs
/
Popular searches
Speech-to-Text
How do I transcribe an audio file?Speech-to-Text overview and modelsWhich ASR model should I use?Streaming ASR over WebSocketASR request parameters and configurationPOST /v1/audio/transcriptionsSpeech-to-TextFull reference
Text-to-Speech
How do I synthesize text to speech?Text-to-Speech overviewVoices, languages, and expression stylesTTS streaming WebSocketAudio formats and telephony codecsLLM to TTS pipeline for voice agentsText-to-Speech
API Reference
API Reference hubHow do I authenticate API requests?API errors and status codesRate limits and quotasRequest IDs and tracing
Models
Compare all models (capability matrix)ASR model picker, zero-indic, universal, medOpen weights on Hugging FaceCapability matrix
Features
ASR features and intelligence flagsBatch vs streaming, when to use which?Speaker registration and identification APIsOverviewWhat is Shunya?QuickstartGlossaryVāķ TranslateBFSI
Intelligence
Intelligence overview with examplesDiarization, who spoke when?Intent detection on transcriptsSentiment analysis and summarizationRedaction, profanity hashing, PII maskingOverview & examplesConfiguration
PlaygroundModelsLog inFree API key
HomeQuickstartSpeech-to-TextText-to-SpeechTranslationIntelligence
ASR API referenceTranscriptions, streaming, speakersTTS API referenceSpeech synthesis, voices, formatsCapability matrixModels, languages, pricing
IntegrationsDeployment
Get Started
OverviewWhat is Shunya?QuickstartCapability matrixGlossary
Speech-to-Text
Text-to-Speech
Intelligence
Overview & examplesConfigurationFull reference
Translation
Vāķ Translate
Solutions
BFSIHealthcareContact centresMedia & entertainment
Integrations
OverviewPython SDKOpenAI SDKSIP / PSTNHugging Face
Deployment
Cloud / on-prem
Enterprise
Set up SSOHands-on evaluation
Security
Compliance & privacy
Docs/Integrations

Platform integrations

SDKs, telephony providers, and platforms that work with Shunya Labs out of the box. Every integration on this page is documented in Shunya's published API guide or SDK reference, pick the one that matches your stack.

Python SDK

First-party shunyalabs package on PyPI. AsyncShunyaClient with async/await, retries, and override URLs for self-hosted deployments.

First-party
OpenAI SDK

The TTS API is OpenAI-compatible. Use the official OpenAI Python SDK, point base_url at Shunya and your existing code keeps working.

Drop-in
SIP / PSTN

Generic telephony pipelines. mulaw for North American and Indian PSTN; alaw for European telephony and many SIP providers.

Telephony
Hugging Face

Open weights at huggingface.co/shunyalabs. Download via huggingface-cli or use the transformers pipeline for local / air-gapped inference.

Self-host
← Previous
Solutions: Media
Next →
Python SDK