Best Free Text-to-Speech APIs in 2026: 8 Providers Compared

If you’re looking for a free text-to-speech API, the honest answer is: it depends on how you define free. Amazon Polly gives you 5M standard characters a month, but only for 12 months and only if you hand over a card. Google Cloud gives 4M Standard characters a month with no expiry, but also requires billing to be enabled first. ElevenLabs and Cartesia skip the card entirely, but cap you at 10K and 20K characters a month. None of these is free in the way “free” usually means online — they’re all free trials of a paid product, gated differently.

Here’s what this guide covers: Fish Audio (backed by Novita AI), ElevenLabs, Google Cloud TTS, Amazon Polly, Microsoft Azure TTS, OpenAI TTS, PlayAI, and Cartesia. All pricing and free-tier terms below are verified from official provider pages as of August 2026.

Free Tier Comparison

Provider	Free Allowance	Duration	Credit Card Required	Source
Google Cloud TTS	4M characters/mo (Standard), 1M characters/mo (WaveNet/Neural2)	No expiry, resets monthly	Yes — billing must be enabled to use the API at all	cloud.google.com/text-to-speech/pricing
Amazon Polly	5M characters/mo (Standard), 1M/mo (Neural), 500K/mo (Long-Form), 100K/mo (Generative)	First 12 months only	Yes — AWS account signup requires a card, with a temporary $1 authorization hold	aws.amazon.com/polly/pricing
Azure TTS	0.5M characters/mo (Neural)	No expiry, resets monthly	Yes, for the standard Azure account (Azure for Students is card-free)	azure.microsoft.com/pricing/details/cognitive-services/speech-services
Cartesia	20K credits/mo (1 credit = 1 character)	No expiry, resets monthly	No	cartesia.ai/pricing
ElevenLabs	10K credits/mo (1 credit = 1 character)	No expiry, resets monthly	No	elevenlabs.io/pricing
Fish Audio via Novita AI	No dedicated TTS free tier; new accounts get a starter voucher usable across all APIs	Voucher is time-limited per Novita’s terms	Depends on payment method chosen at signup	novita.ai/docs/guides/quickstart
OpenAI TTS	None	—	—	No published free tier as of this check
PlayAI	None published on the pricing page; PAYG and subscription tiers only	—	—	No published free tier as of this check

Google Cloud’s 4M characters/month Standard allowance is the largest ongoing free tier with no expiration date — that’s the pick if you want to prototype indefinitely without a deadline. Amazon Polly’s 5M/month is larger on paper but disappears after 12 months. Cartesia and ElevenLabs are the only two that don’t ask for a credit card up front, which matters if you just want to test voice quality before committing to anything.

Fish Audio via Novita AI does not carry a TTS-specific free allowance the way Google or Amazon do — new accounts get a starter voucher that applies across the whole platform (LLMs, image, video, and audio APIs), not a ring-fenced TTS quota. If your priority is “try TTS for $0 today” rather than “cheapest at scale,” start with Google Cloud, Cartesia, or ElevenLabs; come back to Fish Audio once you’re ready to pay per character at $15/1M with no subscription lock-in.

Quick Comparison

Provider	Voices	Languages	Voice Cloning	Price (per 1M chars)	Best For
Fish Audio	20+	10	✅ $0.1/voice	$15.00	Voice cloning at $0.1/voice + 44.1kHz quality
ElevenLabs	3,000+	29	✅ Instant + Pro	$120–$300	Strong naturalness scores (Artificial Analysis)
Google Cloud TTS	220+	40+	❌ Enterprise only	$4–$160	GCP ecosystem, SSML power users, largest ongoing free tier
Amazon Polly	60+	30+	❌	$4–$100	AWS ecosystem, largest free-tier allowance for the first 12 months
Microsoft Azure TTS	400+	140+	✅ Personal Voice	$16–$100	Enterprise, broadest language coverage among providers checked
OpenAI TTS	10	~57	❌	$15–$30	OpenAI pipeline users
PlayAI	900+	142	✅ Instant	$15–$100	Multi-voice conversations
Cartesia	150+	42	✅	Credit-based, 20K credits/mo free	Real-time voice AI (<100ms), no card required to start

Pricing last verified: August 24, 2026. Check provider pages before purchase.

What to Look for in a TTS API

• Latency: Real-time agents need <300ms. Batch workflows tolerate async.
• Voice quality: Benchmarked by Artificial Analysis Speech Arena across 73 models.
• Language and voice coverage: From 10 voices / English-only (Deepgram) to 400+ voices / 140+ languages (Azure).
• Emotion control: From none (Polly Standard) to 50+ SSML styles (Azure) to explicit enum params (MiniMax via Novita AI).
• Pricing model: Subscription (ElevenLabs), flat PAYG (Cartesia, Novita AI), or cloud-account billing (Polly, Google).

Fish Audio — Best Voice Cloning API for Multilingual Developers

Fish Audio’s speech model delivers 44.1kHz output quality, voice cloning from 10–30 seconds of audio at $0.1/voice, and supports 10 languages including English, Chinese, Japanese, Korean, and Arabic. It’s accessible via Novita AI’s API at $15/1M characters — no subscription required.

Key Specs

• Model: s1 (Fish Audio v4beta, via reference_id parameter)
• Voices: 20 built-in voices across 10 languages (English, Chinese, Japanese, Korean, Spanish, French, German, Russian, Arabic, Portuguese) — 1 male + 1 female per language
• Audio quality: 44,100 Hz sample rate, up to mp3/opus/wav/pcm output
• Max input: 10,000 characters per request
• Latency modes: normal (for long-form content) / balanced (for shorter, time-sensitive synthesis)
• Voice cloning: $0.1 per voice — upload 10–30 seconds of audio, get a reusable voice_id

Quick Start

Call the v4beta endpoint and get the audio URL synchronously:

import requests

API_KEY = "YOUR_NOVITA_KEY"

response = requests.post(
    "https://api.novita.ai/v4beta/txt2speech",
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    },
    json={
        "text": "Hello, this is Fish Audio TTS.",
        "reference_id": "s1",  # default model
        "format": "mp3",
        "sample_rate": 44100
    }
)

audio_url = response.json()["audio_url"]
print("Audio URL:", audio_url)

Voice Cloning Workflow

Fish Audio voice cloning takes three API calls: upload audio → create clone → use the returned voice_id in any TTS request.

import base64, requests, time

API_KEY = "YOUR_NOVITA_API_KEY"
BASE_URL = "https://api.novita.ai"

# Step 1: Upload audio
with open("sample_voice.mp3", "rb") as f:
    encoded = base64.b64encode(f.read()).decode("utf-8")

file_id = requests.post(
    f"{BASE_URL}/v1/files",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={"file": encoded, "purpose": "voice-cloning"}
).json()["file_id"]

# Step 2: Clone voice
task_id = requests.post(
    f"{BASE_URL}/v1/async/voice-cloning",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={"model": "fish-audio-voice-cloning", "audio_file_id": file_id,
          "text": "Hello, this is a sample text matching the audio content."}
).json()["task_id"]

# Step 3: Get voice_id
while True:
    result = requests.get(f"{BASE_URL}/v1/async/task-result",
        headers={"Authorization": f"Bearer {API_KEY}"},
        params={"task_id": task_id}).json()
    if result["status"].endswith("SUCCEED"):
        voice_id = result["result"]["voice_id"]
        print(f"Cloned voice ID: {voice_id}")
        break
    # add a short poll interval here

# Step 4: Use cloned voice with v4beta TTS
response = requests.post(
    "https://api.novita.ai/v4beta/txt2speech",
    headers={"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"},
    json={
        "text": "Hello, this is my cloned voice.",
        "reference_id": voice_id,  # from Step 3
        "format": "mp3",
        "sample_rate": 44100
    }
)
audio_url = response.json()["audio_url"]
print("Audio URL:", audio_url)

Pros

• Voice cloning at $0.1/voice — well-priced voice cloning among providers checked
• 44.1kHz sample rate output — higher fidelity than most providers (OpenAI outputs at 24kHz)
• 10,000 character limit per request — 2.4× OpenAI’s 4,096 limit
• Multiple output formats: mp3, opus, wav, pcm
• Accessible via Novita AI — same account covers LLMs, image generation, and video generation

Cons

• Async-only — not suitable for real-time sub-200ms applications
• Smaller built-in voice library than ElevenLabs (3,000+) or PlayAI (900+)

Pricing

$15.00 per 1M characters for TTS. $0.1 per voice (one-time, reuse the voice_id indefinitely). No subscription required — pure pay-as-you-go.

Best for: Developers building multilingual apps, LLM-to-voice pipelines, or applications that need branded/custom voices without committing to a single-vendor TTS stack.

ElevenLabs — Strong Voice Quality

ElevenLabs remains the benchmark for raw voice naturalness. Multilingual v2 supports 29 languages with the most expressive output available; Flash v2.5 hits ~75ms latency for real-time use cases. The 3,000+ voice library is one of the largest available.

Pros

• 3,000+ voices — largest library
• Flash v2.5 at ~75ms latency
• Instant + Professional voice cloning

Cons

• Subscription-only, no flat PAYG on the consumer plans
• Free plan has no commercial usage rights
• Proprietary SDK

Pricing

Free: $0/mo (10K credits, no card required). Starter: $6/mo (30K credits). Creator: $22/mo (121K credits, first month $11). Pro: $99/mo (600K credits). Scale: $299/mo (1.8M credits, 3 seats). Business: $990/mo (6M credits, 10 seats). 1 credit = 1 character for standard TTS.

Best for: Audiobooks, dubbing, podcast production, and any use case where voice naturalness is the primary metric.

Google Cloud Text-to-Speech — Best for GCP Ecosystem Users

Google Cloud TTS covers 40+ languages and 220+ voices with full SSML support. The Standard tier at $4/1M is among the cheapest for high-volume production, and the 4M free characters/month on Standard voices — the largest ongoing free allowance on this list — makes it easy to prototype without a deadline.

Pros

• 4M free characters/month on Standard voices, 1M/month on WaveNet/Neural2/Chirp 3 HD — no expiration date
• Full SSML, 220+ voices, 40+ languages
• Chirp 3 HD voices for higher-fidelity output than Standard/WaveNet

Cons

• No self-service voice cloning (Instant custom voice under Chirp 3 is a separate, no-free-tier feature)
• Studio tier at $160/1M is expensive

Pricing

Standard: $4/1M (4M chars/mo free). WaveNet/Neural2: $16/1M (1M chars/mo free). Chirp 3 HD: $30/1M (1M chars/mo free). Instant custom voice: $60/1M (no free tier). Studio: $160/1M (1M chars/mo free). Billing must be enabled on the project before any usage, free or paid.

Best for: GCP-native stacks, accessibility applications, and high-volume batch synthesis where Standard voice quality is sufficient.

Amazon Polly — Largest Free-Tier Allowance for AWS Users

Amazon Polly’s free tier — 5M Standard characters, 1M Neural characters, 500K Long-Form characters, and 100K Generative characters per month, all for the first 12 months — is the largest allowance on this list. The catch: it requires an AWS account, which requires a credit card up front (AWS places a temporary authorization hold during signup verification). Speech Marks (word-level timestamps) make it the go-to for synchronized visual + audio experiences.

Pros

• Free tier: 5M Standard + 1M Neural + 500K Long-Form + 100K Generative chars/month for 12 months
• Speech Marks for word-level audio-text sync
• Native AWS integration

Cons

• No self-service voice cloning
• Free tier requires a credit card at AWS signup and expires after 12 months
• Generative voices (most natural) are English-only

Pricing

Standard: $4/1M. Neural: $16/1M. Generative: $30/1M. Long-Form: $100/1M. Free tier: 5M Standard + 1M Neural + 500K Long-Form + 100K Generative characters per month (first 12 months only).

Best for: AWS-native applications, IVR systems, and animated/synchronized media that needs Speech Marks.

Microsoft Azure TTS — Broad Language Coverage

Azure has 400+ voices across 140+ languages — the widest coverage of any provider here. The SSML mstts:express-as tag supports 50+ speaking styles per voice (cheerful, sad, angry, newscast, customer-service, and more) with adjustable intensity via styledegree. Personal Voice clones a voice from roughly one minute of audio. Azure’s free tier gives 0.5M Neural characters/month with no expiration date, but signing up for a standard Azure account requires a credit card (Azure for Students is the card-free exception).

Pros

• 140+ languages — widest coverage
• 50+ SSML speaking styles with adjustable intensity
• Personal Voice: clone from ~1 minute of audio

Cons

• Custom Voice Professional Voice pricing (used for advanced neural HD synthesis) runs up to $48/1M
• SSML adds markup complexity
• Free tier requires a credit card for account verification (except Azure for Students)

Pricing

Neural/Neural HD Flash (real-time and batch, us-east region): $15/1M. Neural HD (real-time and batch): $22/1M. Custom Voice Professional Voice synthesis: $24/1M ($48/1M for neural HD synthesis). Personal Voice synthesis: $24/1M. Free tier (F0): 0.5M Neural characters/mo, no expiration. Prices vary by region — the values above are for the us-east region as of this check.

Best for: Enterprise applications requiring 100+ language support, accessibility tooling, and branded voice deployments.

OpenAI TTS — Best for Existing OpenAI Users

If you’re already in the OpenAI ecosystem, gpt-4o-mini-tts is worth using — it accepts a natural language instructions parameter to control tone, pacing, and style without separate SSML markup. The tradeoff: only 10 voices, no voice cloning, and a 4,096 character per request limit.

Pros

• gpt-4o-mini-tts supports instruction-following for emotion and style in plain English
• ~57 language support
• Standard OpenAI Python/JS SDK — no new library to install
• Streaming support for lower perceived latency

Cons

• Only 10 built-in voices — least selection of any provider here
• No voice cloning
• 4,096 character limit per request (Fish Audio allows 10,000)
• $15/1M for tts-1 — more expensive than Google Standard ($4/1M) for equivalent use

Pricing

tts-1: $15/1M chars. tts-1-hd: $30/1M chars. gpt-4o-mini-tts: token-based pricing (see openai.com/api/pricing). The $15–$30 range in the comparison table refers to tts-1 and tts-1-hd only.

Best for: Developers already using OpenAI APIs who want TTS without adding another vendor.

PlayAI — Best for Multi-Voice Conversations

PlayAI’s PlayDialog model is purpose-built for two-agent dialogue — two distinct voices in one API call, synchronized with natural turn-taking. It supports 142 languages (the widest here) and instant voice cloning from under 10 seconds of audio.

Pros

• 142 languages — widest coverage on this list
• 900+ voices
• PlayDialog: two simultaneous voices in one request (unique capability)
• Instant voice cloning from <10 seconds of audio
• WebSocket and gRPC streaming options

Cons

• PlayDialog at $100/1M is expensive for standard TTS use cases
• Proprietary auth (API key + User ID) adds minor integration friction
• Newer ecosystem — less community documentation than ElevenLabs or Google

Pricing

PAYG: PlayHT 2.0 Turbo $15/1M, PlayHT 2.0/3.0 $30/1M, PlayDialog $100/1M. Subscriptions: Creator $39/mo (500k chars) through Scale $999/mo (33M chars).

Best for: Podcasts, audio dramas, interactive voice applications requiring multi-speaker dialogue, and deployments needing broad language coverage.

Cartesia — Best for Real-Time Voice AI

Cartesia’s Sonic model achieves sub-100ms time-to-first-audio — the lowest reported time-to-first-audio among providers checked. It’s built WebSocket-first for real-time streaming applications and offers voice cloning from seconds of audio, making it well-suited for real-time voice AI applications.

Pros

• Sub-100ms time-to-first-audio — no other provider on this list matches this for real-time
• Credit-based pricing: 1 credit = 1 character, with a free tier that needs no credit card
• WebSocket-first API for real-time streaming
• Voice cloning from seconds of audio
• 42 languages with Sonic 3.5

Cons

• 100+ stock voices — smaller library than ElevenLabs or Azure
• 42 languages — solid multilingual support, though narrower than Azure (140+) or PlayAI (142)
• Emotion control via vector embedding — more complex to implement than enum parameters
• Smaller ecosystem and less documentation than established providers

Pricing

Credit-based: 1 credit per character. Free: $0/mo (20K credits/mo, no card required). Pro: $5/mo (100K credits/mo). Startup: $49/mo (1.25M credits/mo). Scale: $299/mo (8M credits/mo). Pricing verified as of this check — see cartesia.ai/pricing.

Best for: Real-time voice agents, conversational AI, customer service bots — any application where latency is the primary constraint.

Use Case Recommendations

Use Case	Best Pick	Why
LLM + TTS in one pipeline	Fish Audio	Same API key for 200+ LLMs and TTS; one billing account
Voice cloning with transparent pricing	Fish Audio	$0.1/voice, reusable voice_id, 10–30s audio required
Highest voice naturalness	ElevenLabs	Multilingual v2 tops quality benchmarks; 3,000+ voices
Real-time voice agents	Cartesia	Sub-100ms, WebSocket-first, credit-based pricing
140+ language enterprise deployment	Azure TTS	400+ voices, 140+ languages, Personal Voice cloning
Multi-voice dialogue	PlayAI PlayDialog	Two-speaker synthesis in one call, 142 languages
Budget AWS/GCP production	Google Cloud / Amazon Polly	$4/1M Standard, generous free tiers
OpenAI ecosystem integration	OpenAI TTS	Same SDK, gpt-4o-mini-tts for style-controlled output

Pricing last verified: August 24, 2026.

Conclusion

No single TTS API wins across every dimension in 2026. The decision comes down to your primary constraint:

• Free with no card, no expiration: Cartesia (20K credits/mo) or ElevenLabs (10K credits/mo)
• Free with the largest ongoing allowance: Google Cloud TTS (4M Standard chars/mo, billing must be enabled)
• Latency: Cartesia (<100ms, credit-based pricing)
• Voice quality: ElevenLabs (Multilingual v2)
• Language coverage: Azure (140+) or PlayAI (142)
• LLM + TTS unified: Fish Audio via Novita AI (one key, one bill, voice cloning at $0.1/voice)
• Budget at scale: Google Cloud Standard or Amazon Polly ($4/1M)

If you’re building an LLM-powered application and want to add voice without a separate vendor, Fish Audio backed by Novita AI is the most practical starting point — the same API key that calls your language model handles TTS and voice cloning.

Frequently Asked Questions

Which TTS API has the best voice quality in 2026?

ElevenLabs Multilingual v2 ranks highest in blind quality tests tracked by Artificial Analysis Speech Arena. For developers who also need voice cloning and multilingual support in one platform, Fish Audio via Novita AI delivers high-quality 44.1kHz output at $15/1M characters.

Which TTS API is cheapest in 2026?

Pricing varies by model and plan. Google Cloud TTS Standard ($4/1M) and Amazon Polly Standard ($4/1M) have the lowest per-character rates at high volume. Cartesia uses a credit-based model (1 credit = 1 character, starting at $5/mo for 100K credits after the free tier).

Which TTS API is actually free?

None of them are free without limits — they’re all free trials of a paid product. Google Cloud TTS gives the largest ongoing allowance with no expiration date: 4M Standard characters/month, though you still have to enable billing to use the API at all. Amazon Polly’s free tier is larger on paper (5M Standard chars/month) but only lasts 12 months and requires a credit card at AWS signup. Cartesia (20K credits/month) and ElevenLabs (10K credits/month) are the only two that don’t ask for a credit card up front. See the free tier comparison table above for the full breakdown.

Which TTS API supports voice cloning?

Fish Audio (via Novita AI), ElevenLabs, PlayAI, Cartesia, and Microsoft Azure Personal Voice all support voice cloning. Fish Audio backed by Novita AI charges $0.1 per voice with a straightforward three-step API workflow: upload audio → clone → get voice_id.

Can I use a TTS API with my existing LLM pipeline?

Novita AI is the only platform offering both 200+ LLMs and multiple TTS engines (Fish Audio, MiniMax, CosyVoice) under one API key and billing account. OpenAI offers LLM + TTS too, but with only 10 voices and no voice cloning. For a fully integrated LLM-to-voice pipeline, Novita AI’s TTS API removes the need for a separate TTS vendor.

Recommended Articles

• Fish Audio S2 Pro Quick Start for Voice Cloning and Multilingual TTS
• GLM TTS and ASR API Quick Start
• Hailuo Voice Cloning with Speech 2.5 on Novita AI