By the SpeechGeneration AI Editorial Team·Apr 17, 2026·Updated July 2, 2026·18 min read

Best AI Text-to-Speech APIs for Developers in 2026

Q: Has PlayHT's shutdown changed how I should pick a TTS API in 2026?

Yes — in two ways. First, infrastructure consolidation is real: Meta's acquisition of PlayHT (July 2025) and the December 31, 2025 API shutdown signal that voice infrastructure is becoming a 6-8 player market. Picking a well-funded provider with a clear roadmap matters more than it did 18 months ago. Second, if you previously used PlayHT's API, closest architectural replacements are Cartesia Sonic-3.5 (WebSocket-first, similar latency profile) and Deepgram Aura-2 (~90ms TTFB with compliance options). LMNT, Rime AI, and Fish Audio are newer entrants targeting the same use case.

A neutral, fact-dense evaluation of 14 production TTS APIs — covering streaming latency (TTFB), pricing per 1M characters, voice cloning, SSML support, and language coverage. Now with Fish Audio S2 added and Cartesia Sonic-3.5 pricing corrected. Updated July 2, 2026.

Quick Verdict

For real-time voice agents in 2026, Cartesia Sonic-3.5 (sub-50ms TTFB class, see our Cartesia vs ElevenLabs comparison) and Rime AI Mist v3 (~37ms P50 on H100) lead on raw latency. Deepgram Aura-2 (~90ms) is the production-grade pick when on-prem and HIPAA matter. For audiobooks and emotional narration, ElevenLabs v3 remains the highest-quality choice; Inworld TTS is the newcomer to watch with 200+ languages on TTS-2 and OpenAI SDK drop-in compatibility. LMNT ships unlimited voice clones on its $10/mo tier and Fish Audio S2 ships 15-second instant cloning + 2M-voice library on its $11/mo Plus tier — both undercut ElevenLabs Professional cloning by an order of magnitude for indie workloads (see our Fish Audio vs ElevenLabs comparison). OpenAI gpt-4o-mini-tts at ~$0.015/min remains the cost leader for prototypes. PlayHT's API was sunset Dec 31, 2025 — migrate to Cartesia, Deepgram, LMNT, or ElevenLabs Flash. SSML is dying; new flagship models use natural-language instructions or proprietary tags instead.

Disclosure: SpeechGeneration AI does not offer a developer API at the latency-and-scale tier covered in this guide. That makes this comparison neutral — we have no API to recommend. We offer SpeechGeneration AI as a content production tool for narration, audiobooks, and multilingual content. For real-time voice apps, use the providers below. Pricing and latency data verified July 2, 2026 from official provider documentation. Where a fact wasn't publicly disclosed, we say so explicitly rather than fill it in.

How We Evaluated These APIs

We did not measure naturalness on a single sentence and call it a ranking. The metrics that actually matter for production engineering are:

Time-to-first-audio (TTFA) / TTFB — vendor-quoted inference time plus real-world network overhead. Under 200ms feels conversational; over 400ms breaks immersion.
Streaming transport — WebSocket (bidirectional), HTTP chunked (one-shot), gRPC (Google).
Cost per 1M characters — the spread is 25× between providers ($4 Polly Standard to $100+ Polly Long-form).
Language coverage and depth — Azure leads on count (140+); Cartesia and ElevenLabs have stronger neural quality per language.
Voice cloning — sample length, commercial terms, instant vs professional tiers.
SSML or alternative style control — most new APIs have dropped SSML.
Compliance — SOC 2, HIPAA BAA, on-prem option.
Reliability at concurrency — vendor latency on a single request is useless; what matters is p99 under 100+ concurrent streams.

Why not just MOS? Top systems cluster within 0.1-0.2 MOS of each other (4.5-4.8). Quality is no longer the differentiator. Latency, languages, and licensing are.

The 2026 TTS API Maturity Quadrant

We rank providers on two axes that actually matter: latency maturity (legacy → real-time-grade, measured by quoted TTFB) and capability breadth (single-purpose → full-stack: streaming + cloning + SSML + language count).

STREAMING-FIRST SPECIALISTS

Sub-200ms TTFB, focused features

Cartesia Sonic-3.5 (sub-50ms class)

Rime AI (~37ms P50 on H100)

Deepgram Aura-2 (~90ms)

LMNT (~150-200ms)

Best for: voice agents, IVR

FULL-STACK LEADERS

Sub-200ms (with Flash/Mini) + cloning + 50+ langs

ElevenLabs v3 (+ Flash tier)

Hume Octave 2

Inworld TTS (200+ langs on TTS-2)

Fish Audio S2 (best Mandarin/JP/KO)

Best for: production apps needing range

CLOUD INCUMBENTS

High capability, latency varies (200-500ms)

Azure AI Speech

Amazon Polly

Google Cloud TTS

Best for: enterprise, regulated

BUDGET / PROTOTYPE TIER

Cheap, lower latency budget

OpenAI gpt-4o-mini-tts

Resemble AI

Best for: prototypes, low-volume

Production Latency Reality Check

Vendor-quoted TTFB is almost always model-inference time on the provider's own hardware. Real production p90 from your backend is consistently higher because of TLS handshake (~50-100ms), regional network RTT, authentication, and concurrency contention. Treat vendor numbers as lower bounds, not expected latency.

Provider / Model	Vendor-quoted	Realistic prod p90 (US backend)	Source / notes
Cartesia Sonic-3.5	Sub-50ms TTFA class	~150-300ms	Vendor benchmark; State Space Model
Rime Mist v3	~37ms P50 / 56ms P90	~150-300ms (cloud) / sub-100ms (on-prem)	Vendor benchmark, H100 hardware
ElevenLabs Flash v2.5	~75ms model inference	~350ms US / ~527ms India	Vendor docs; end-to-end
Deepgram Aura-2	~90ms optimized	~200-350ms	Vendor docs
Hume Octave 2	~100ms generation	~250-400ms	Vendor docs
Inworld TTS 1.5 Mini	~120ms median / sub-130ms P90	~250-400ms	Vendor docs
LMNT streaming	~150-200ms TTFB (marketing range)	~300-500ms	Marketing; no detailed benchmark
Inworld Realtime TTS-2	~200ms P50 / <250ms P90	~350-550ms	Vendor docs
ElevenLabs Multilingual v2	~250-300ms inference	~478ms TTFB measured (REST/PCM)	Picovoice benchmark Q1 2026
AWS Polly Generative (streaming)	Sub-second, region-dependent	~500-900ms	Bidirectional streaming added Mar 2026

How to use this table: If your latency budget is sub-300ms p90 (live conversational agents), shortlist the top three rows. If sub-500ms is acceptable (most voice apps), most providers in the table will work. WebSocket pooling is required to hit the lower end — connection setup alone adds ~230ms.

Sources: official provider documentation (ElevenLabs, Cartesia, Deepgram, Hume, Inworld, Rime, LMNT, AWS), Picovoice latency benchmarks, and the Artificial Analysis TTS leaderboard. We did not independently measure these numbers — production p90 estimates assume typical US backend (TLS + 80ms RTT + WebSocket pooling). Real numbers depend heavily on your region and concurrency.

The 14 Best TTS APIs Reviewed

Each review uses the same skimmable format. Pricing and feature data verified June 2026 from official provider documentation.

1. ElevenLabs API

Best balance of quality and developer experience — the default pick for content-grade TTS.

Pricing: Flash v2.5 at $0.06/1K chars (~$60/M); Multilingual v2 and v3 at $0.12/1K chars (~$120/M)

Streaming: WebSocket + HTTP chunked. Flash ~75ms model TTFB, ~350ms end-to-end (US); Multilingual ~250-300ms

Voice cloning: Instant Voice Clone (1 min sample, Creator tier+), Professional Voice Clone (30+ min fine-tune, identity verification required)

Languages: 70 languages in v3, 32 in Flash/Turbo

SSML / style: Largely deprecated in v3 — uses inline audio tags like [whispers] [nervous] [laughs]

SDKs: Python, Node/TS, Java, Go, Swift, Kotlin, .NET — best-in-class docs. Free tier: 10K credits/month

Best for: Audiobooks, character voices, agent voices where quality > raw cost

Avoid if: Budget-constrained at scale, or need sub-100ms TTFB

2. Cartesia Sonic-3.5

The latency leader — sub-50ms TTFA class, State Space Model architecture.

Pricing: Pro $5/mo (100K credits), Startup $49/mo (1.25M credits), Scale $299/mo (8M credits). Verified June 2026 at cartesia.ai/pricing.

Streaming: WebSocket-first, sub-50ms TTFA class, ~90ms model latency. Distributed via AWS SageMaker JumpStart (Feb 2026)

Voice cloning: 3-second clip instant clone, 10-second higher quality, Pro Voice Clone at 1.5 credits/char

Languages: 42, including 9 Indic languages (strong Hindi)

SSML / style: None; uses implicit prosody from the LLM-codec architecture

SDKs: Python, Node/TS, plus LiveKit + Pipecat integrations

Best for: Real-time voice agents, IVR, game NPCs, Indic-language products

Avoid if: Need full SSML, need strict W3C compliance

3. Google Cloud Text-to-Speech

Maximum flexibility for GCP-stack apps, but pricing tiers are a maze.

Pricing: Standard/WaveNet $4/M, Neural2/Polyglot $16/M, Chirp 3: HD $30/M, Studio $160/M, Instant Custom Voice $60/M

Streaming: gRPC + REST; Chirp 3: HD supports text-streaming for agents

Voice cloning: Instant Custom Voice (limited availability)

Languages: 50+ languages, 380+ voices

SSML / style: Near-full W3C on Standard/WaveNet/Neural2/Studio. ZERO SSML on Chirp 3: HD (critical gotcha when porting from Neural2)

SDKs: 7+ official languages. Free tier: 4M chars/mo Standard + 1M WaveNet + 1M Chirp 3

Best for: GCP-native apps, accessibility, multilingual reach

Avoid if: Migrating from Neural2 to Chirp 3 (you lose all SSML)

4. Amazon Polly

The AWS-integration default, now with bidirectional streaming for Generative.

Pricing: Standard $4/M, Neural $16/M (some sources cite $19.20/M), Generative $30/M, Long-form $100/M

Streaming: HTTP chunked for all engines; bidirectional streaming API for Generative launched March 2026 (US-East/West, Frankfurt, London, Singapore, Canada)

Voice cloning: Not self-serve API — Brand Voice is bespoke enterprise engagement

Languages: Neural in 36 languages; Long-form English-only (6 voices: Danielle, Gregory, Ruth, Patrick, Alba, Raúl)

SSML / style: Full W3C SSML plus custom Amazon tags (Newscaster style, breathing, whisper)

SDKs: Every AWS SDK language. Free tier: 5M Standard / 1M Neural / 100K Long-form & Generative chars/mo for 12 months

Best for: AWS-stack IVR, e-learning, document narration at scale

Avoid if: Not on AWS, or need real-time below 200ms in older engines

5. Azure AI Speech

Broadest language coverage and enterprise compliance leader.

Pricing: Neural real-time/batch $16/M, Long Audio $100/M, Custom Neural Voice $24/M plus endpoint hosting per-second

Streaming: WebSocket + REST + Speech SDK (SDK is the production path)

Voice cloning: Personal Voice (~60 sec consumer-style), Professional Neural Voice (gated, requires recorded consent + business case)

Languages: 140+ languages, 500+ neural voices — the broadest of any major provider

SSML / style: Full W3C SSML with rich Microsoft extensions (<mstts:express-as>, style-degree, role, viseme)

SDKs: C#, C++, Java, Python, Node, Go, Swift, Objective-C. Free tier: 500K chars/mo Neural

Best for: Enterprise IVR, regulated industries, accessibility, brand voice with compliance needs

Avoid if: Simple use cases (overkill); need sub-100ms TTFB

6. OpenAI TTS API

The new cost leader for prototypes — but no streaming WebSocket, no SSML, no cloning.

Pricing: tts-1 at $15/M, tts-1-hd at $30/M; gpt-4o-mini-tts at $0.60/M input tokens + $12/M audio output tokens (~$0.015/min)

Streaming: HTTP chunk-transfer only. No WebSocket TTS (Realtime API is a different surface)

Voice cloning: None

Languages: 50+

SSML / style: None. Uses natural-language instructions: 'Speak in a cheerful, sympathetic tone'

SDKs: Python, Node, .NET, Go, Java. 13 voices: Alloy, Ash, Ballad, Coral, Echo, Fable, Nova, Onyx, Sage, Shimmer, Verse, Marin, Cedar

Best for: Prototypes, ChatGPT-style assistants, multilingual narration on a budget

Avoid if: Need streaming WebSocket, need voice cloning, need SSML

7. Deepgram Aura-2

Production-grade latency with strong on-prem and compliance story.

Pricing: $0.030/1K chars ($30/M); Growth tier $0.027/1K

Streaming: WebSocket + HTTP. Sub-200ms baseline TTFB, ~90ms optimized

Voice cloning: Not offered

Languages: 7 (English, Spanish, Dutch, French, German, Italian, Japanese); 40+ English voices, 10+ Spanish

SSML / style: None — deliberately. Uses entity-aware text normalization for phone numbers, addresses, account numbers

SDKs: Python, Node/TS, .NET, Go, Rust — modern, async-first. Free tier: $200 credit

Best for: Real-time voice agents, telephony, healthcare/regulated IVR (SOC 2 II + HIPAA BAA, on-prem air-gapped option)

Avoid if: Need more than 7 languages, need cloning, need SSML

8. Hume AI Octave 2

The emotional intelligence leader — TTS that understands what it's saying.

Pricing: $7.60/M chars (Oct 2025 launch dropped price ~50%); Business overage $0.05/1K

Streaming: HTTP chunked + WebSocket. ~100ms generation, sub-200ms total

Voice cloning: Instant clones from 5-15 second samples

Languages: 16+ with native accents

SSML / style: None — uses natural-language emotional instructions ('sound sarcastic', 'whisper fearfully'). The model is an LLM that understands text and adjusts prosody to semantic and emotional intent

SDKs: TypeScript, Python, .NET

Best for: Empathetic agents, mental wellness apps, character-driven narrative, emotion-critical use cases

Avoid if: Pure speed/cost optimization (other providers are faster or cheaper for non-emotional content)

9. LMNT

Voice agent specialist with unlimited cloning on every paid tier — including the $10/mo Indie plan.

Pricing: Free (15K chars/mo), Indie $10/mo (200K chars, $0.05/1K overage), Pro $49/mo (1.25M chars, $0.045/1K), Premium $199/mo (5.7M chars, $0.035/1K)

Streaming: Full-duplex WebSocket speech sessions + HTTP streaming. Provider-quoted <300ms; marketing cites 150-200ms TTFB range. No gRPC.

Voice cloning: Instant clone from ~15 seconds of audio; higher-quality clone from ~5 minutes. Unlimited voice clones on every tier. Commercial license included on paid plans.

Languages: 31 languages

SSML / style: No documented W3C SSML. Parameter-based control via stability, expressiveness, language

SDKs: Python, Node/TypeScript, Go, plus cURL examples. Community Unity SDK. Free tier: 15K characters/month with free voice clones — no card required

Best for: Voice agents and real-time conversational apps where unlimited clones + flat-rate pricing matter

Avoid if: Need full W3C SSML, need gRPC, need ElevenLabs-grade audio-tag prosody control

10. Rime AI

Customer-support voice agents specialist — sub-100ms on-prem TTFB, bilingual EN/ES, HIPAA/SOC 2 ready.

Pricing: Per-character with subscription. Starter ~$0.03/1K characters with 3,000 minutes included. Model-specific rates: Mist $0.03/1K, Arcana $0.04/1K, Coda $0.05/1K. Enterprise custom.

Streaming: HTTP streaming PCM endpoint (no WebSocket or gRPC documented). Provider-quoted sub-200ms cloud TTFB, sub-100ms on-prem. Mist v3 benchmarks at ~37ms P50 / 56ms P90 on H100 hardware.

Voice cloning: Available only on Enterprise tier ("unlimited custom TTS voice clones"). Not offered on self-serve Starter. Sample length not publicly disclosed.

Languages: Arcana v3: 10 languages. Mist: focused on English + Spanish bilingual. 300+ voices total.

SSML / style: Proprietary markup/SSML-like tags for pronunciation control and homograph disambiguation — not full W3C SSML

SDKs: Python and JS/TS via REST; HTTP-first. Integrations with LiveKit, Vapi, Bolna, Together AI

Best for: Customer-support voice agents and high-volume telephony — bilingual EN/ES, sub-100ms on-prem, on-prem/VPC deployment, HIPAA/SOC 2 compliance

Avoid if: Need voice cloning on self-serve tiers, need 30+ languages, need WebSocket streaming

11. Inworld TTS

Character-AI specialist turned full-stack contender — OpenAI SDK drop-in, 200+ languages on TTS-2, free instant cloning.

Pricing: On-Demand (free start), $25/1M chars (Realtime TTS-2). Subscription tiers: Creator $25/mo ($20/1M), Builder $100/mo ($17.50/1M), Developer $300/mo ($15/1M), Growth $1,500/mo ($12.50/1M), Enterprise from $5/1M. TTS 1.5 Mini scales down to $5/1M.

Streaming: WebSocket bidirectional + HTTP streaming POST. Realtime TTS-2 ~200ms P50 / <250ms P90. TTS 1.5 Max <200ms median. TTS 1.5 Mini ~120ms median / <130ms P90.

Voice cloning: Instant clone from 5-15 seconds (free for all users, zero-shot). Professional clone needs 5-30+ min clean audio (sales-gated; one included on Growth tier).

Languages: Realtime TTS-2: 200+ languages/locales. TTS 1.5 Max/Mini: 15 languages each.

SSML / style: Not publicly disclosed as W3C SSML. Supports custom pronunciation and prosody temperature parameter.

SDKs: First-party Python (inworld-tts on PyPI, 3.10+) and Node/TypeScript. OpenAI SDK drop-in compatibility (swap base_url to api.inworld.ai/v1).

Best for: Character AI, AI companions, games (Inworld's original focus); multilingual voice agents needing 200+ languages; teams migrating from OpenAI TTS via base_url swap

Avoid if: Need W3C SSML compliance, need a long-proven roadmap (newest entrant in this guide)

12. Fish Audio S2

Best budget cloning + strongest Mandarin/Japanese/Korean; open-source Fish-Speech backbone.

Pricing: Free tier, Plus $11/mo (250K credits, 10 private voice clones), Pro $75/mo (2M credits + unlimited slots + 5 pro clones), Max $749/mo (25M credits). Verified June 2026 at fish.audio/plan.

Streaming: REST + WebSocket streaming; ~200ms typical TTFB (not sub-50ms class). Best-suited for batch generation and voiceover, not real-time voice agents.

Voice cloning: 15-second instant clone (10 private slots on Plus, unlimited on Pro). Also: 2M+ voice community library for character voice variety without creating clones. Cross-lingual cloning supported.

Languages: 8+ core (English, Chinese Mandarin/Cantonese, Japanese, Korean, French, German, Arabic, Spanish); documentation references 80+ tiered language support

SSML / style: None — uses inline emotion tags similar to ElevenLabs v3 approach

SDKs: Python and JS/TS. Open-source Fish-Speech v1.5.1 (~30K GitHub stars, Fish Audio Research License) available for self-hosting on H100/H200 GPU infrastructure.

Best for: Mandarin/Japanese/Korean voice cloning, budget-conscious cloning workflows (10 private clones for $11/mo), teams wanting an open-source migration path

Avoid if: Need sub-100ms TTFB for real-time voice agents (use Cartesia or Rime), need 30+ languages with consistent quality (use ElevenLabs v3)

13. Resemble AI

Best for branded voices and on-prem/regulated deployments.

Pricing: Creator $30/mo, Professional $60/mo, custom enterprise + pay-as-you-go Flex credits

Streaming: WebSocket and REST; real-time tier gated to higher plans

Voice cloning: Rapid Voice Clone (short, fast) and Professional Voice Clone (longer, higher fidelity); commercial use included on paid plans

Languages: ~149 marketed (largely translation/cross-lingual)

SSML / style: Supported with custom emotion tags

SDKs: Python + REST examples. Bonus: open-source Chatterbox/Chatterbox Turbo (MIT licensed, ~75ms latency on GPU, paralinguistic [laugh][cough] tags) for self-hosting

Best for: Custom branded voices, on-prem/air-gapped deployments, voice-locked media

Avoid if: Simple use cases (pricing/UX optimized for enterprise)

14. PlayHT (Play 3.0 mini)DISCONTINUED

Discontinued. Migrate to Cartesia, Fish Audio, or ElevenLabs Flash — see our Play.ht migration guide.

Pricing: N/A — API shut down December 31, 2025

Streaming: Historic: Play 3.0 mini hit 143ms mean TTFB, supported WebSocket + REST + Python SDK

Voice cloning: Historic: instant voice cloning, ~30 languages

Languages: N/A

SSML / style: N/A

SDKs: N/A

Best for: Migration: Cartesia Sonic-3.5 is the closest architectural replacement; ElevenLabs Flash and Fish Audio Plus are workable secondary paths

Avoid if: Always — the API is no longer available. Any tutorial citing PlayHT in 2026 is outdated.

Decision Matrix: Which API for Which Use Case

Use Case	Primary Pick	Secondary	Why
Real-time voice agent (LiveKit/Pipecat)	Cartesia Sonic-3.5	Deepgram Aura-2, LMNT	40-90ms TTFA, WebSocket-native
Customer-support voice agent (telephony)	Rime AI (Mist v3)	Deepgram Aura-2	Sub-100ms on-prem, HIPAA/SOC 2, bilingual EN/ES
Telephony / IVR (regulated)	Azure AI Speech	Deepgram (on-prem), Rime AI	SSML, compliance, broad languages
AWS-stack IVR / e-learning	Amazon Polly Generative	Polly Neural	Native AWS, bidirectional streaming
Long-form audiobooks	ElevenLabs v3	Polly Long-form, Azure Long Audio	Prosody and emotional range
Empathetic / wellness apps	Hume Octave 2	ElevenLabs v3	Semantic emotion model
AI character / game NPC voice	Inworld TTS	Hume Octave 2	Character AI focus, 200+ langs on TTS-2
Voice clone on a tight budget (unlimited clones)	LMNT (Indie $10/mo)	Fish Audio Plus, ElevenLabs Creator	Unlimited clones on $10/mo tier; Fish Audio Plus at $11/mo for 10 private clones + 2M public voice library
Mandarin / Japanese / Korean voice cloning	Fish Audio S2 (Plus $11/mo)	ElevenLabs v3	S2 model excels in East Asian languages — 15-sec instant clones
Migrating from OpenAI TTS	Inworld TTS (base_url swap)	Cartesia Sonic-3.5	OpenAI SDK drop-in compatibility
Cheap prototype / hackathon	OpenAI gpt-4o-mini-tts	Google Chirp 3 HD	$0.015/min, easy SDK
Brand voice / branded clone	Resemble AI or ElevenLabs PVC	Azure Custom Neural Voice	Commercial cloning + compliance
Multilingual (50+ langs)	Azure	Inworld TTS-2, ElevenLabs v3, Resemble	Coverage
200+ language coverage	Inworld Realtime TTS-2	Azure (140+)	Largest published language count in 2026
Indic languages	Cartesia Sonic-3.5	Resemble	9 Indic langs, strong Hindi
Self-host / air-gapped	Resemble Chatterbox (OSS)	Deepgram on-prem, Rime on-prem	MIT-licensed, GPU-deployable
Migrating from PlayHT API	Cartesia Sonic-3.5	ElevenLabs Flash, Fish Audio Plus, Deepgram Aura-2	Closest architectural match to Play 3.0 mini — see our /compare/speechgenerationai-vs-playht migration guide
Accessibility / bulk screen readers	Google Cloud Standard ($4/M)	Polly Standard	Cheapest competent voices

Surprising Facts About TTS APIs in 2026

#1PlayHT shut down its public API on December 31, 2025

Meta acquired PlayHT in July 2025, and the API was permanently sunset at end-of-year 2025. Cartesia Sonic-3.5 is the closest architectural replacement. Any guide citing PlayHT in 2026 is outdated.

#2Google Chirp 3: HD does not support SSML at all

Despite being Google's flagship $30/M voice. Teams porting from Neural2 lose every <break>, <prosody>, and <emphasis> tag. This is one of the most consequential undocumented gotchas in the GCP TTS migration path.

#3Cartesia Sonic-3.5 hits sub-50ms TTFA — 5-10× faster than ElevenLabs Multilingual v2

Achieved via State Space Model architecture (not a transformer). This is the first major TTS architecture shift since neural vocoders, and it's already changing what real-time voice agents can do.

#4OpenAI's gpt-4o-mini-tts at ~$0.015/min undercuts ElevenLabs' cheapest tier by ~50%

And has no usage gating on voice cloning because it doesn't offer cloning at all. The cost story for prototypes has flipped — what was a Cohere/ElevenLabs decision a year ago is now an OpenAI default.

#5Top TTS now scores within 0.1-0.2 MOS of human speech

In blind tests, ~38% of listeners can't tell the best AI from a real person. Quality is no longer the differentiator. Latency, languages, and licensing are.

#6LMNT ships unlimited voice clones on its $10/month tier

Most competitors gate cloning behind $20+/mo tiers or enterprise plans. LMNT's Indie tier ($10/mo, 200K chars) includes unlimited voice clones with commercial use — a structurally cheaper path to multi-voice apps than ElevenLabs Creator or Hume.

#7Inworld TTS is an OpenAI SDK drop-in replacement

Swap base_url to api.inworld.ai/v1 and existing OpenAI TTS code works against Inworld at a fraction of the per-character cost. Realtime TTS-2 also exposes 200+ languages — more than Azure, which has been the multilingual leader.

#8Rime Mist v3 benchmarks at ~37ms P50 TTFA on H100 — and it's HTTP-only

Among the fastest publicly reported numbers in the industry, achieved via HTTP streaming PCM rather than WebSocket. Rime targets customer-support telephony with sub-100ms on-prem latency, HIPAA/SOC 2, and bilingual EN/ES focus.

Myths to Debunk

Myth #1: "SSML is the standard — every TTS API supports it."

Reality: ElevenLabs v3, Cartesia, Deepgram Aura-2, Hume Octave, OpenAI TTS, and Google's Chirp 3 HD have all dropped SSML in favor of bracket tags, natural-language instructions, or implicit prosody. Polly and Azure are the holdouts.

Myth #2: "Per-second pricing is replacing per-character pricing."

Reality: Mostly marketing. Per-character is still industry standard. What's changed is the rate (down ~50% on premium tiers over 18 months), not the unit.

Myth #3: "ElevenLabs is the highest-quality TTS available."

Reality: Not on independent benchmarks. As of Artificial Analysis (June 2026), Realtime TTS 1.5 Max (Elo 1208) and Gemini 3.1 Flash TTS (Elo 1206) outrank Eleven v3 (Elo 1178) on blind preference. ElevenLabs has the deepest voice library and best developer experience, but it's not the quality leader anymore.

How TTS APIs Work — Quick Primer

Picking a TTS API is easier when you understand what's actually happening under the hood — the encoder-decoder architecture, why streaming TTFB varies between providers, when SSML helps vs. hurts, and how voice cloning compares zero-shot to fine-tuned.

Read our full How TTS APIs Work guide →

Frequently Asked Questions

Which TTS API has the lowest latency in 2026?

Cartesia Sonic-3.5 (sub-50ms TTFA class) and Rime AI Mist v3 (~37ms P50 on H100 hardware) lead vendor-reported benchmarks. Deepgram Aura-2 (~90ms optimized), ElevenLabs Flash v2.5 (~75ms model inference), Hume Octave 2 (~100ms), and Inworld TTS 1.5 Mini (~120ms) cluster in the sub-200ms tier. All vendor numbers are inference-only; production p90 from your backend will be 200-500ms US and 400-700ms Asia after TLS, region RTT, and network jitter. Always measure from your own infrastructure.

What's the cheapest production-grade TTS API in 2026?

OpenAI gpt-4o-mini-tts at ~$0.015/minute is the cost leader for premium-quality output. Google Cloud Standard at $4/M characters wins for bulk static content (screen readers, accessibility). For streaming quality with WebSocket, Deepgram Aura-2 at $30/M is competitive. ElevenLabs Flash at ~$60/M is the budget option in the ElevenLabs ecosystem. Fish Audio Plus $11/mo includes 10 voice clones + 250K credits — the cheapest cloning-inclusive path.

Do all TTS APIs support voice cloning?

No. ElevenLabs, Cartesia, Resemble, Hume, Fish Audio, LMNT, and Azure support voice cloning. OpenAI, Deepgram, Google Cloud (mostly), and Amazon Polly self-serve tier do not. Sample length varies dramatically: 3 seconds (Cartesia Instant), 5-15 seconds (Fish Audio S2, Hume Octave, LMNT), to 30+ minutes (ElevenLabs Pro Voice Clone, AWS Polly Brand Voice). Commercial terms vary — verify consent and rights requirements per provider.

Is SSML still useful in 2026?

For Polly and Azure legacy support and strict W3C-compliance use cases (regulated industries, accessibility tools that consume SSML upstream), yes. For most new builds, natural-language style instructions (OpenAI pattern) or inline audio tags (ElevenLabs v3, Fish Audio S2) are more expressive and easier to maintain. ElevenLabs v3, Cartesia, Deepgram Aura-2, OpenAI TTS, Hume Octave, and Google Chirp 3 HD have all dropped SSML.

Why did PlayHT shut down?

Meta acquired PlayHT in July 2025; the public API was sunset December 31, 2025, presumably to consolidate the team's work into Meta's voice infrastructure. Cartesia Sonic-3.5 is the closest architectural replacement (WebSocket-first, sub-50ms TTFB class, voice cloning). ElevenLabs Flash and Fish Audio Plus are workable secondary migration paths. Any tutorial citing PlayHT API in 2026 is outdated. See our Play.ht migration guide for use-case-specific paths.

WebSocket or HTTP streaming — which should I use?

Use HTTP chunked streaming when text is already fully in hand (narration, audiobooks, document reading). Use WebSocket when text is streaming from an upstream LLM and you want TTS to start before the LLM finishes (voice agents, live transcription readback). WebSocket adds ~230ms handshake overhead per connection — pool connections in production. Standard pattern: pre-warm a WebSocket pool so connection setup is amortized across requests.

How do I avoid getting locked into one TTS API?

Three patterns. First, wrap each provider behind a common synthesize(text, voice, format) → audio interface. Second, maintain voice ID mappings per provider with a fallback 'closest equivalent' matrix. Third, test critical use cases on at least two providers quarterly. Cartesia and ElevenLabs offer the cleanest abstraction layer with their SDKs. For maximum portability, consider self-hosting an open-weights model (Fish-Speech, F5-TTS, StyleTTS 2, XTTS-v2) as a fallback layer.

What is the lowest measured production TTFB for a TTS API in 2026?

Vendor-quoted numbers and measured production p90 are not the same thing. As of June 2026, the lowest publicly reported production-grade numbers are: Cartesia Sonic-3.5 (sub-50ms class), Rime Mist v3 (~37ms P50 / 56ms P90 on H100), Inworld TTS 1.5 Mini (~120ms median / <130ms P90), Deepgram Aura-2 (~90ms optimized), ElevenLabs Flash v2.5 (~75ms model inference). Real-world end-to-end p90 from a US backend is typically 200-500ms after TLS, network, and application overhead. Measure from your own infrastructure before committing.

Has PlayHT's shutdown changed how I should pick a TTS API in 2026?

Yes — in two ways. First, infrastructure consolidation is real: Meta's acquisition of PlayHT (July 2025) and the December 31, 2025 API shutdown signal that voice infrastructure is becoming a 6-8 player market. Picking a well-funded provider with a clear roadmap matters more than it did 18 months ago. Second, if you previously used PlayHT's API, closest architectural replacements are Cartesia Sonic-3.5 (WebSocket-first, similar latency profile) and Deepgram Aura-2 (~90ms TTFB with compliance options). LMNT, Rime AI, and Fish Audio are newer entrants targeting the same use case.

Related Resources

How TTS APIs Work

Architecture, streaming, SSML, voice cloning — the technical foundation

Best TTS Technology (Developer Guide)

Deeper look at modern TTS architecture

SG.ai vs Competitors 2026

Feature matrix for content production tools

SG.ai for Power Users

Verdict for advanced content production workflows

SG.ai vs ElevenLabs

Content-tool comparison

Advanced Features Pricing

Production-tier pricing breakdown

Play.ht Migration Guide

Where to move Play.ht workflows after the API shutdown

Best Voice Cloning Tools 2026

6-tool ranking by use case for the cloning-specific decision

About the Editorial Team

This guide is maintained by the SpeechGeneration AI Editorial Team. We ship a production TTS product used by narration, audiobook, and multilingual content teams, and we consume the same TTS APIs we review here for internal tooling — WebSocket integrations for demo playback, batch generation for benchmarking, and voice-cloning stacks for research comparisons.

How we research pricing and latency. Every provider entry is sourced from the vendor's current public pricing page, official API documentation, and — where available — published benchmark posts (Picovoice, Artificial Analysis, vendor engineering blogs). We do not accept payment, affiliate commission, or promotional consideration from any provider named on this page. Where a data point isn't publicly disclosed, we say so explicitly rather than infer.

Why we're a neutral source. SpeechGeneration AI does not sell a developer API in the sub-100ms streaming class. Our product is a content-production tool for narration and multilingual voice work — a different market than the 14 providers reviewed here. That structural non-overlap is why we're comfortable naming a specific competitor in each row of the Decision Matrix. If we did sell a competing API, this page would read very differently, and you should be more skeptical of listicles from vendors who do.

How to reach us. If you spot a factual error — a stale price, a shipped feature we missed, a vendor benchmark we cited that has since been retracted — email hello@speechgeneration.ai. We publish corrections in the Page Changelog below with the date and the reason for the change.

Page Changelog

Apr 17, 2026: Initial publication. 10 provider reviews verified against official documentation. Quadrant framework, decision matrix, 5 surprising facts, 3 myths debunked. PlayHT marked discontinued (shutdown confirmed Dec 31, 2025).
June 21, 2026: Added 3 providers (LMNT, Rime AI, Inworld TTS) with verified pricing, latency, cloning, and language data sourced from official documentation. Added new Production Latency Reality Check table comparing vendor-quoted TTFB to realistic production p90 estimates. Expanded decision matrix from 11 to 17 use cases including customer-support voice agents (Rime), AI character voices (Inworld), and PlayHT migration. Added 3 surprising facts and 2 FAQs. Reverified pricing for all existing providers; the cost story is largely unchanged from April. Maturity quadrant updated to place the new providers; ElevenLabs remains the default content-grade pick but Cartesia and Rime split the "lowest TTFB" lead.
July 2, 2026: Added Fish Audio S2 as the 14th provider (rank 12) — 15-second instant clone, strongest Mandarin/Japanese/Korean coverage, open-source Fish-Speech backbone; verified pricing (Plus $11/mo, Pro $75/mo, Max $749/mo) via fish.audio/plan. Corrected Cartesia pricing to Pro $5 / Startup $49 / Scale $299 (was $4/$39/$239) and renamed model to Sonic-3.5 across every reference. Updated Decision Matrix with a new Mandarin/JP/KO row and expanded PlayHT-migration secondaries to include Fish Audio Plus. Refreshed FAQs to cover Fish Audio, the sub-50ms TTFA class framing, and the cross-lingual cloning economics. Added Editorial Team byline block and expanded Sources notes for E-E-A-T. Metadata rewritten: title now "Best TTS APIs for Developers (2026): 14 Providers Verified July 2" and description tightened under 160 chars. Added ArticleStructuredData for publishing schema.

Contents