Text-to-speech (TTS)BYOK supported

OpenAI TTS for AI voice agents

OpenAI TTS is one of the voices you can run a Telenow AI voice agent on. Predictable cost, 6 stock voices. Give your agent a OpenAI TTS voice for natural, streaming speech the caller can't tell from a human. Mix and match it with any LLM, STT, TTS and carrier — Telenow is component-level, so you're never locked in.

Last updated 2026-09-16

OpenAI TTS voices

Non-streaming~540ms6 voices

Alloy · EnglishEcho · EnglishFable · EnglishOnyx · EnglishNova · EnglishShimmer · English

Frequently asked questions

Can I use a OpenAI TTS voice for my AI agent?+

Yes — pick a OpenAI TTS voice in Telenow and your agent speaks with it on every call, streaming so there's no awkward pause.

What voices does OpenAI TTS offer?+

Alloy, Echo, Fable, Onyx, Nova, and Shimmer — choose by language, gender and style in the builder.

Does OpenAI TTS stream speech in real time?+

OpenAI TTS generates the reply, then the agent speaks it.

How much does OpenAI TTS cost for a voice agent?+

You pay OpenAI TTS's usage at cost plus Telenow's transparent platform fee — billed per component (speech, model, telephony) and per minute, with new accounts getting free signup credit to try it.

Can I bring my own OpenAI TTS API key?+

Yes. Telenow supports BYOK — paste your own OpenAI TTS key to bill OpenAI TTS usage to your account, or use the platform key and pay through Telenow.

Other text-to-speech (tts) options

Telenow in-house TTS — 22 Indian languages + English, voice cloning & design; μ-law 8k telephony, 24k HD on web calls.

Most natural prosody; great for branded voices.

Lowest-latency streaming TTS (Sonic); near-realtime, μ-law 8k direct.

Grok streaming TTS — expressive voices + your xAI voice clones, speech tags (laugh, sigh, pause) when expression is on; μ-law 8k telephony, 24k HD on web calls.

Soniox real-time TTS — 60+ languages with one voice speaking them all (strong Hindi + code-switching), plus instant cross-lingual voice cloning; μ-law 8k telephony, 24k HD on web, gapless streaming.

AWS Polly neural voices — cheap, many languages, μ-law telephony output.

Real-time multilingual TTS — low latency, 30+ languages, low cost.

Conversational US-English with accents/dialects; sub-100ms.

Sarvam (Indian languages)

Bulbul — Hindi + 10 Indian languages & Indian-English accents.

Smallest.ai (Lightning)

Ultra-low-latency TTS — 225+ voices, 30+ languages incl. Indian.

Expressive, emotional TTS. Higher latency — warmth over speed.

Low-cost streaming TTS — Kokoro voices across English (US/UK) & Hindi.

Google Gemini TTS

Gemini 3.1 Flash TTS — 30 voices that each speak 90+ languages, directed in plain English: you write the speaker, the scene and the accent (Indian, American, British…) and the same voice performs it. Inline tags ([whispers], [laughs], [excited]) steer delivery mid-sentence when expression is on. Synthesised a whole turn at a time so the performance never drifts between clauses; μ-law 8k telephony, 24k HD on web.

Custom TTS (bring your own endpoint)

Point at any streaming-HTTP TTS endpoint. Describe the request body + audio format once; we reframe the audio to telephony μ-law. MVP: streaming HTTP (mulaw / pcm16 / mp3).

$1.00 free credit on signup

Build a voice agent with OpenAI TTS

Sign up free and get $1.00 in credit — no card required. Connect your number, pick a template, and go live in minutes.

Sign up Talk to sales