Onepin launches August 11, 9 AM PT.
30 featured voice models across 18 providers. A selection of what Onepin routes to, planned and validated through the same pipeline.
30 models
Studio-grade multilingual speech with wide locale coverage and full SSML. Best-in-class Chinese and Cantonese.
Stability, similarity, style exaggeration and speed (0.7 to 1.2).
Alpha flagship with inline audio-tag emotion ([whispering], [laughing]) across 70+ languages. The most expressive ElevenLabs model.
Audio tags ([whispering], [laughing], [excited]) plus stability, similarity and style exaggeration.
Balanced quality and speed with audio markup tags and instant cloning; sub-250ms latency for interactive use.
Stability, similarity, style and speed.
Lowest-latency ElevenLabs model (~75ms) for real-time agents, with strong Chinese and Cantonese and 300+ voices.
Stability, similarity and speed (limited expression).
Ultra-low-latency speech on state-space models, with sub-100ms streaming and on-device deployments for real-time agents.
Speed, emotion, pause/pacing, volume and voice mixing.
The fastest Sonic tier, with pacing tags and cross-lingual cloning tuned for high-throughput, latency-critical apps.
Speed and pause/pacing tags with faster, lighter cloning.
Expressive, production-grade conversational speech with deterministic phoneme control, built for audio at scale.
Phoneme tags, emotion via Arcana tags and pause control.
Low-latency conversational model with 300+ voices and deterministic IVR pronunciation for high-volume agents.
Speed, deterministic IVR pronunciation and pause control.
Korea's market-leading TTS, with premium Korean voices plus English, Japanese and Chinese, avatar video and cloning.
Emotion (where supported), speed, pitch, volume and pause.
Studio-grade, ethically-sourced voice cloning used by EA, Sony and Lucasfilm; speech-to-speech that captures a real performance.
Pitch, emotion and formant driven by a reference performance (speech-to-speech), plus de-noising.
DeepMind WaveNet voices across 40+ languages with full SSML control. The workhorse for high-volume, multilingual pipelines.
SSML prosody (rate/pitch/volume), emphasis, breaks, say-as and phoneme tags.
#1 on the HuggingFace TTS Arena (2025): low-latency, expressive speech with inline audio markups and instant cloning at a very low price.
Audio markups, instant voice cloning and sub-250ms latency.
The most expressive Inworld tier, with richer audio markups and instant cloning, tuned for character and narrative work.
Richer audio markups plus instant voice cloning.
Japan-focused TTS with a huge anime and character-voice marketplace, plus a Japanese phoneme dictionary for precise pronunciation.
Speed, pitch, intonation, per-voice emotion and pause control.
Steerable OpenAI voices driven by a natural-language instructions field ('speak slowly and warmly'). Simple, fast and inexpensive.
Natural-language instructions field ('speak slowly and warmly') plus speed.
Sub-200ms conversational English TTS built for voice agents, with SSML phoneme control and a natural, on-brand delivery.
Speed, pitch and volume via SSML, emphasis tags and a conversational style.
The Max tier of Inworld's 1.5 line, with inline IPA control and expressive non-verbal markers for real-time agents.
Inline IPA, non-verbal markers and emphasis (full NL steering on TTS-2).
Multilingual HD flagship (Jan 2026) with deep controllability: emotion, voice mixing, pinyin/Jyutping tones and IPA dictionaries.
Emotion, speed/pitch/volume, voice mixing, pause and interjection tags, plus IPA dictionaries.
Gemini-native TTS with natural-language style prompts and 200+ expressive audio tags across single- and multi-speaker output.
Natural-language style prompts and 200+ expressive audio tags ([whispers], [laughs]).
Inworld's research-preview flagship (May 2026), #1 on the Artificial Analysis Speech Arena, with LLM-style natural-language steering.
Natural-language steering in [brackets], three stability modes and audio-context conditioning.
Microsoft's newest MAI flagship TTS (Build 2026 preview) with expressive styles, multi-speaker and long-form via Azure Speech SSML.
Expressive styles with style degree, 15+ emotions, multi-speaker and long-form.
Cartesia's May-2026 flagship: #1 on the Artificial Analysis Speech Arena with ~82ms latency, 50+ emotions and IPA dictionaries.
Speed and volume, 50+ emotions, <break> and <spell> tags and pronunciation dictionaries.
A sub-100ms naturalness leader (Coval bench) tuned for effortless, hands-off conversational speech, with deliberately minimal controls.
Minimal by design: playback speed and voice selection only.
Expressive successor to S1 with open-ended [bracket] emotion tags, 64+ expressions and ~100ms latency; strong CJK coverage.
Open-ended [bracket] emotion tags, 64+ expressions and paralinguistics (laugh, sigh, whisper).
Azure's neural voices with the broadest language coverage in the market: full SSML, emotional styles and custom lexicons.
Full SSML: prosody, emotional styles (cheerful/sad/angry) and viseme output.
Azure's HD tier: natural, conversational delivery that adapts tone in context, with full SSML and custom lexicon support.
Natural conversational tone with speed and full SSML.
Studio-friendly voices for content teams, with a pronunciation library, IPA overrides and simple speed, pitch and emphasis controls.
Speed, pitch, emphasis, pause and pronunciation overrides.
Enterprise narration voices with a word-level pronunciation library and IPA overrides, tuned for consistent brand tone.
Speed, emphasis and pause/breath via the in-app editor, tuned for brand tone.
Massively multilingual TTS (140+ languages) with cross-lingual voice transfer and reference-audio emotion for global dubbing.
Reference-audio emotion, speed, age and gender, plus cross-lingual voice transfer.
Amazon's long-form TTS for audiobooks and podcasts, with custom lexicons and full SSML phoneme control across 30+ languages.
Designed for long-form audio (audiobooks, podcasts) with full SSML.
Point us to a voice model. We’ll run it through the same benchmarks as everything here.