The Skeptic

xAI's STT and TTS APIs — fast, accurate, claimed best price

“'Best price' is a marketing claim without a published pricing page. xAI has a history of infrastructure unpredictability and rate limit surprises. Wait for independent benchmarks and a stable pricing tier before migrating anything production from Deepgram or ElevenLabs.”

Google's new TTS API: 70 languages, 200+ audio tags, native multi-speaker

“It's Google — which means it could be deprecated in 18 months and replaced with Gemini 4 Flash TTS Pro Ultra. The audio tags sound creative but until there's a published spec for all 200+ of them, you're guessing at prompt-engineering your voice model. And SynthID watermarking is only as useful as the detection ecosystem, which is still nascent.”

Free, local ElevenLabs alternative with voice cloning and a stories editor

“Running five different TTS engines locally means significant disk and RAM footprints. Quality will still trail ElevenLabs' latest models for professional use cases. The stories editor sounds great in theory but multi-track voice timelines are notoriously fiddly — wait for v1.0 stability.”

Open-source ASR that beats Whisper in accuracy and speed

“The 14-language support sounds broad but there's a big quality gap between English and the tail languages. And Whisper's massive community, fine-tuning ecosystem, and tooling integration will keep it dominant in practice even if Cohere wins on raw WER scores.”

Build, test & deploy voice AI agents with full LLM/TTS control

“The voice AI agent space is brutally competitive right now — Vapi, Retell, ElevenLabs Conversational AI all have deeper ecosystems. And most MCP integrations are still fragile in production. Being 'developer-first' in a space dominated by enterprise contracts is a tough position.”

Full voice + vision AI running locally on your Mac — no cloud needed

“Three-second latency is still noticeably clunky for natural conversation — OpenAI and Google's voice APIs run in under a second. On older Macs or non-Apple hardware the latency will be worse. It's a proof of concept, not a daily driver, and the model quality gap between Gemma 4 E2B and GPT-4o voice is real.”

Open-source ASR model topping HuggingFace leaderboard — free API, 14 languages, enterprise-ready

“5.42% WER on benchmark data is good but benchmarks measure clean, lab-quality audio. Real enterprise audio — phone calls, meeting rooms, accented speakers, domain jargon — is a different world. I'd want to see numbers on domain-specific test sets before migrating anything production off Whisper or Deepgram.”