{"language":"Telugu","locale":"te-IN","measuredAt":"2026-08-15","method":"Three isolated production make_tts adapter instances at 8 kHz PCM16; await Azure built-in connection/model warm-up; start perf_counter immediately before speak(text); stop at first non-empty audio chunk; cancel after first chunk; report median; exclude STT, model, carrier and playback.","runtime":{"grade":"Bharat Standard","provider":"Azure Speech","vendorVoice":"en-IN-NeerjaIndicNeural","displayVoice":"Neerja Indic","sttProvider":"Sarvam saaras:v3","engine":"cascade","getVoicePackResult":"None from the generic business integration","resolvedPack":"te-IN dedicated pack"},"benchmarkText":"నమస్కారం, మీకు ఎలా సహాయం చేయగలను?","latencyRunsMs":[577,608,823],"medianFirstAudioMs":608,"packSamples":[{"purpose":"Filler while a tool runs","text":"ఒక్క క్షణం అండి","registerNote":"A short polite spoken-Telugu hold line."},{"purpose":"Retry after unclear speech","text":"క్షమించండి అండి, ఒక్కసారి మళ్ళీ చెప్తారా?","registerNote":"Polite conversational retry with అండి."},{"purpose":"Retract an unsupported action","text":"క్షమించండి, అది నేను ఇక్కడ నుంచి పంపలేను. మీ నంబర్ తీసుకుంటాను, ఎవరైనా మీకు పంపిస్తారు.","registerNote":"A direct retraction followed by a human fallback."}],"honestLimits":["Google WaveNet has no Telugu voice, so Bharat Essential cannot serve te-IN and the benchmark uses Bharat Standard.","Azure's native te-IN-ShrutiNeural and te-IN-MohanNeural voices were retired after the 2 Aug 2026 owner audition; runtime resolution rewrites either old selection to an Indic multilingual voice.","The production Telugu voice is en-IN-NeerjaIndicNeural reading Telugu script, not a native te-IN voice identifier.","The 608 ms median excludes the built-in Azure connection and model warm-up, which the production adapter performs during call setup before the measured turn.","The first-audio benchmark measures TTS adapter latency only; it excludes caller speech recognition, model reasoning, carrier transit and handset playback."]}