AI voice models: the wrap-up comparison
Prices rechecked 14 Nov. Hume's old TTS docs now redirect, Chatterbox's README calls the repo an archive, and the main API prices still match.
Topic · 18 stories
18 stories tagged text-to-speech on AI Tamer, newest first.
Prices rechecked 14 Nov. Hume's old TTS docs now redirect, Chatterbox's README calls the repo an archive, and the main API prices still match.
DeepSeek's 13 November API release adds server-run web search, file parsing, URL reading, TTS, ASR and a safety check to deepseek-flash, with per-use prices.
Voxtral Mini TTS 3 is $13 per million characters with an agent SDK; MAI-Voice-2.1 is $22, Flash $15, with gated cloning. How the two compare, checked 10 Nov.
ZONOS3-Mini is an 800M-parameter MoE text-to-speech model with about 100M active, Apache-2.0 weights, voice cloning and runtimes for browsers, Macs and SGLang.
Three open-weight TTS picks: Kokoro's tiny Apache model, Resemble's MIT Chatterbox family with cloning, and Fish Audio Drama 3, the top open model on AA.
Cartesia's Sonic 3.6 ranks 4th for TTS from $37 per million characters. Hume's Octave and EVI APIs shut on 13 Nov. Ranks, cloning rules and a migration plan.
Grok Voice 3.0 at $0.08 a minute, TTS at $15 per million characters, verified voice cloning and 20+ languages. Ranks, limits, rights and the gaps.
AssemblyAI-TTS-1 is GA for voice agents: six languages, 4,000+ voices, instant cloning and about 90 ms to first audio, with no concurrency fees.
OpenAI is retiring its TTS models for realtime voice; Google doubled down on cheap TTS. GPT-Live 1, Realtime 2.1 and Gemini 3.8 TTS on twelve questions.
ElevenLabs' Eleven v4 and v4 Turbo hold the top two arena spots. Cloning, languages, latency, prices, the new Realtime v1 and what users say.
Voxtral 3 pairs new Mistral transcription and speech models with a LiveKit-based voice agent SDK, on Mistral's API or self-deployed.
Fish Audio released Drama 3 weights for scripted multi-speaker speech. Commercial use is free under a $500,000 revenue cap. It is not an OSI license.
Azure Speech lets applications choose encoded audio characteristics. Match the codec, sample rate, channels, and header format to the browser or phone pipeline before naming or forwarding the bytes.
SSML can request a slower, softer or higher voice, but the synthesizer decides how to render it. Design voice prompts around audible outcomes and a usable fallback.
ElevenLabs launched Eleven v4 and Eleven v4 Turbo (published Sep 28, 2026; page updated Oct 1)—emotive text-to-speech for agents and creative work, available now in ElevenAgents, ElevenCreative, and ElevenAPI.
A practical guide to Whisper, Parakeet, Canary, Kokoro, and Piper, with a clear way to compare word error rate and check model licenses.
A practical map of speech recognition, language models, speech synthesis, direct speech-to-speech models, streaming, and the latency measurements that matter.
Google launched Gemini 3.8 Flash TTS and Flash-Lite TTS on 2026-09-23 — promptable voice design, 2,000+ voices, and consent-gated replication. Pricing from ai.google.dev: Flash $0.50/$9 and Lite $0.50/$6 through 2026-12-31.