Sarvam

Sarvam AI covers three surfaces, each on the SDK's existing protocols. One key (SARVAM_API_KEY) drives all of them.

Chat

Sarvam chat has its own first-class model:

let result = try await generateText(
  model: SarvamModel("sarvam-105b"),
  prompt: "मुझे भारत के बारे में एक तथ्य बताओ।"
)

Base URL https://api.sarvam.ai/v1, Authorization: Bearer auth. Tools, structured output, and streaming ride the shared chat-completions path.

The chat models are sarvam-30b (64K context) and sarvam-105b (128K context), both reasoning models: reasoning goes out as reasoning_effort, and the model's thinking streams back as .reasoningDelta.

let result = try await generateText(
  model: SarvamModel("sarvam-105b"),
  prompt: "Prove that √2 is irrational.",
  reasoning: .high
)
print(result.reasoningText)
print(result.text)

Text to speech

SarvamSpeechModel calls the Bulbul voices. Sarvam requires a target language; set it on the model or per request. It uses the shared generateSpeech API:

let tts = SarvamSpeechModel("bulbul:v3", targetLanguage: "hi-IN")
let audio = try await generateSpeech(
  model: tts,
  text: "नमस्ते, आप कैसे हैं?",
  voice: "anushka",              // → speaker
  speed: 1.1,                    // → pace
  outputFormat: "mp3"            // → output_audio_codec
)

The language override and Sarvam-only knobs (pitch, loudness, temperature, speech_sample_rate) go through providerOptions:

try await generateSpeech(
  model: SarvamSpeechModel(),     // defaults to bulbul:v3, en-IN
  text: "வணக்கம்",
  providerOptions: ["target_language_code": "ta-IN", "temperature": 0.7]
)

Auth is the api-subscription-key header. Audio comes back base64-encoded and is decoded for you; outputFormat sets the returned media type (defaults to audio/wav).

Transcription

SarvamTranscriptionModel posts the audio as multipart to the Saaras models through the shared transcribe API. Language and mode ride through providerOptions:

let stt = SarvamTranscriptionModel("saaras:v3")
let result = try await transcribe(
  model: stt,
  audio: audioData,
  mediaType: "audio/wav",
  providerOptions: ["language_code": "hi-IN", "mode": "transcribe"]
)
print(result.text)          // transcript
print(result.language)      // detected language_code

mode accepts transcribe, translate, verbatim, translit, or codemix.