# 7 best text to speech APIs for healthcare calls in 2026

By Samuel Oram-Jones

A health system's compliance team usually asks a speech vendor one question before anyone listens to a voice: will the vendor sign a business associate agreement, known as a BAA, the contract HIPAA requires before a vendor handles patient information on a provider's behalf. Seven text to speech APIs answer that question in different ways, and the answers decide who gets a pilot.

A voice that sounds read out can lose a patient in the first second, which is why Bland Speech leads: Bland Speech v3 ranked first of 13 AI voices in Design Arena's Audio Realism Bench results of 4 August 2026. Amazon Polly and Google make more sense for a team that already works under an AWS or Google Cloud BAA, as of November 2026.

## What are the best text to speech APIs for healthcare calls?

The best text to speech API for healthcare calls in 2026 is Bland Speech, followed by Rime, Amazon Polly, Google, Microsoft Azure, ElevenLabs, and Deepgram, with Bland Speech first on how its voice sounds on a phone line.

- **Bland Speech:** Best overall for patient phone calls that should sound like a person
- **Rime:** Best for healthcare voice agents that need a BAA and a dedicated or on-premises deployment
- **Amazon Polly:** Best for teams whose BAA is already the AWS one
- **Google:** Best for teams whose BAA is already Google Cloud's
- **Microsoft Azure:** Best for teams on a Microsoft agreement that need 100+ languages and locales
- **ElevenLabs:** Best for patient lines in many languages, with 90+ on its newest models
- **Deepgram:** Best for teams that want speech recognition and speech from one vendor that signs a BAA

| API | BAA position, as the company states it | Phone audio (mu-law) | Price as the company publishes it | Audio Realism Bench, 4 August 2026 |
|---|---|---|---|---|
| Bland Speech | Bland is HIPAA compliant with a signed BAA | Yes | $0.04 per 1,000 characters | #1 AI voice, 1365 |
| Rime | HIPAA compliant, BAA available | Yes | $0.030 to $0.050 a minute | Wasn't in those results |
| Amazon Polly | HIPAA Eligible Service under the AWS BAA | Yes | $4 to $100 per million characters, by engine | Wasn't in those results |
| Google | Text-to-Speech on Google Cloud's BAA list | Yes | $30 per million characters for Chirp 3: HD | Gemini 2.5 Pro TTS: #5, 1109 |
| Microsoft Azure | BAA through Microsoft's Product Terms | Yes | $15 per million characters for Neural voices | MAI-Voice-2: #2, 1224 |
| ElevenLabs | BAAs for qualifying healthcare enterprises | Yes | $0.04 to $0.08 per 1,000 characters, by model | Eleven v3: #12, 938 |
| Deepgram | BAA for Enterprise customers | Yes | $0.015 to $0.045 per 1,000 characters, by model | Wasn't in those results |

<details><summary>What these rows mean</summary>

- **BAA position:** each company's own wording. Amazon and Google tie the BAA to a named service, Microsoft ties it to its Product Terms, and the others tie it to a company or a plan.
- **Price:** each company's list price with the model or engine named. Rime bills by the minute and says a minute is about 1,000 characters.
- **Audio Realism Bench:** the rank among 13 AI voices and the score in Design Arena's published results.

</details>

Patient calls go to Bland Speech first on the strength of that 4 August 2026 realism result, 8 kHz phone audio, and a company-wide HIPAA position, while a team already working under an AWS or Google Cloud BAA can start from Amazon Polly or Google.

## What should a health system check in a text to speech API?

A health system should check four things in order: how the vendor offers a BAA, whether audio comes back in the format phone lines use, whether the voice passes for a person, and what happens to the text after it is spoken.

### How does each vendor offer a BAA?

Amazon says Polly is a HIPAA Eligible Service covered under the AWS Business Associate Addendum, and Google names Text-to-Speech among the products its BAA covers. Microsoft says no separate contract is needed, because its BAA comes with the Microsoft Product Terms. Rime, Deepgram, and ElevenLabs each offer a BAA, with Deepgram and ElevenLabs tying it to Enterprise customers.

Bland is HIPAA compliant with a signed BAA and SOC 2 Type II audited, and Bland says speech synthesis runs inside its FedRAMP boundary.

### What phone audio does a patient line need?

US phone networks carry mu-law, a compressed 8-bit format sampled at 8 kHz, and an API that can't return it leaves a team converting audio on every call. All seven APIs here return it, so phone audio separates none of them and the choice moves to voice and contract terms.

### What happens to the text after it is spoken?

Patient text is the sensitive part of a speech request. Microsoft says neither input text nor output audio is stored in its logs for prebuilt voices in real-time synthesis, Rime keeps no customer data beyond a character count by default, and ElevenLabs and Bland each offer zero-retention processing as an option.

## How do the 7 best text to speech APIs for healthcare calls compare?

These seven differ most in how human they sound, how each one offers a BAA, and how each one bills.

### 1. Bland Speech: Best overall for patient phone calls that should sound like a person

**What does it do?** Bland Speech is the text to speech model inside Bland, a voice AI provider that runs its own speech model for enterprise phone calls. Text streams in over HTTP or over a WebSocket that takes text as a language model writes it, and audio comes back as PCM from 8 to 48 kHz or as mu-law at 8 kHz. Tags such as [say warmly], [say quietly], and [voice lowered] shape delivery inline, and a new context on the WebSocket cancels the turn that is playing, so a patient can talk over the agent. The [text to speech API](/text-to-speech-api) page has the endpoints.

<div class="cmp-proscons cmp-proscons-own"><div class="cmp-proscons-pros"><p><strong>Pros</strong></p><ul><li>Bland Speech v3 ranked first of 13 AI voices on Audio Realism Bench on 4 August 2026</li><li>Bland is HIPAA compliant with a signed BAA, and SOC 2 Type II audited</li><li>One standard rate, $0.04 per 1,000 characters, with no monthly plan</li></ul></div><div class="cmp-proscons-cons"><p><strong>Cons</strong></p><ul><li>More than a one-off narration needs, because Bland Speech is built for production calls</li></ul></div></div>

**Pricing:** $0.04 per 1,000 characters, which is $40 per million, with 50,000 characters free for a new account, and Bland's own example puts a 60-second note at $0.04. Bland puts the BAA under Enterprise. Enterprise pricing is custom, set with Bland's sales team. The [Bland Speech](/speech) page has a studio to try a voice.

### 2. Rime: Best for healthcare voice agents that need a BAA and a dedicated or on-premises deployment

**What does it do?** Rime sells conversational voice models, with Coda and Mist v3 for text to speech, and says they are built for voice agents, IVR, and telephony in healthcare, financial services, and other regulated industries. They stream over HTTP, WebSocket, and gRPC, and they return G.711 mu-law at 8 kHz.

<div class="cmp-proscons" data-rival="rime"><div class="cmp-proscons-pros"><p><strong>Pros</strong></p><ul><li>Rime says it has been HIPAA compliant since February 2024, with its latest audit completed in March 2026</li><li>SOC 2 Type 2 compliant, and a BAA available</li><li>Dedicated VPC or on-premises deployment for enterprise customers</li></ul></div><div class="cmp-proscons-cons"><p><strong>Cons</strong></p><ul><li>Coda's cloud API serves 10 languages, and 185 of its 313 voices are English</li><li>Voice cloning is an enterprise order placed with Rime</li><li>Its voices weren't in Audio Realism Bench's results of 4 August 2026</li></ul></div></div>

**Pricing:** On the Flex plan, $0.030 a minute for Mist v3 and $0.050 a minute for Coda v2, and the Free plan includes $50 of usage every month. Rime's Enterprise plan includes a BAA and a SOC 2 Type II report. [Bland Speech vs Rime](/compare/bland-speech-vs-rime) compares the two.

### 3. Amazon Polly: Best for teams whose BAA is already the AWS one

**What does it do?** Amazon Polly offers four voice engines, Generative, Long-Form, Neural, and Standard, streams audio over HTTP, and returns mu-law and A-law at 8 kHz.

<div class="cmp-proscons" data-rival="amazon-polly"><div class="cmp-proscons-pros"><p><strong>Pros</strong></p><ul><li>A HIPAA Eligible Service under the AWS BAA</li><li>Standard voices at $4 per million characters</li></ul></div><div class="cmp-proscons-cons"><p><strong>Cons</strong></p><ul><li>No self-serve voice cloning, with Brand Voice as an engagement through an AWS account manager</li><li>Its voices weren't in Audio Realism Bench's results of 4 August 2026</li></ul></div></div>

**Pricing:** $4 per million characters for Standard voices, $16 for Neural, $30 for Generative, and $100 for Long-Form, with free tier allowances by engine.

### 4. Google: Best for teams whose BAA is already Google Cloud's

**What does it do?** Google Cloud Text-to-Speech offers Chirp 3: HD voices, Gemini-TTS models priced by token, and older WaveNet, Neural2, and Standard voices across 75+ languages and variants, and it returns mu-law and A-law.

<div class="cmp-proscons" data-rival="google"><div class="cmp-proscons-pros"><p><strong>Pros</strong></p><ul><li>Text-to-Speech is on the list of products Google's HIPAA BAA covers</li><li>The first million Chirp 3: HD characters are free each month</li></ul></div><div class="cmp-proscons-cons"><p><strong>Cons</strong></p><ul><li>Chirp 3: Instant Custom Voice is closed to new access requests</li><li>Gemini-TTS models come with no free usage</li></ul></div></div>

**Pricing:** $30 per million characters for Chirp 3: HD after the first free million each month, $4 for WaveNet and Standard, and $16 for Neural2. Gemini 2.5 Pro TTS ranked 5th of 13 AI voices on Audio Realism Bench on 4 August 2026, and Chirp 3: HD voices weren't in those results.

### 5. Microsoft Azure: Best for teams on a Microsoft agreement that need 100+ languages and locales

**What does it do?** Azure Speech offers neural voices in 100+ languages and locales, neural HD voices, custom voices, and Microsoft's MAI-Voice-2.1 models in public preview, and it returns mu-law and A-law at 8 kHz.

<div class="cmp-proscons" data-rival="azure"><div class="cmp-proscons-pros"><p><strong>Pros</strong></p><ul><li>A BAA through Microsoft's Product Terms, with no separate contract</li><li>Input text and output audio aren't stored in Microsoft's logs for prebuilt voices in real-time synthesis</li></ul></div><div class="cmp-proscons-cons"><p><strong>Cons</strong></p><ul><li>MAI-Voice is in public preview, without a service-level agreement, and Microsoft doesn't recommend it for production workloads</li><li>Custom voices are limited to customers Microsoft manages directly</li></ul></div></div>

**Pricing:** $15 per million characters for Neural and Neural HD Flash voices, with 0.5 million characters free a month. MAI-Voice-2 ranked 2nd of 13 AI voices on Audio Realism Bench on 4 August 2026, and Azure Speech offers MAI-Voice-2.1 models today, with no public price shown for MAI-Voice.

### 6. ElevenLabs: Best for patient lines in many languages, with 90+ on its newest models

**What does it do?** ElevenLabs sells text to speech, transcription, and voice agents. Eleven v4 and v4 Turbo launched on 28 September 2026 and speak 90+ languages, and the API returns mu-law at 8 kHz.

<div class="cmp-proscons" data-rival="elevenlabs"><div class="cmp-proscons-pros"><p><strong>Pros</strong></p><ul><li>90+ languages on the Eleven v4 family</li><li>BAAs for qualifying healthcare enterprises, with Zero Retention Mode as an option</li></ul></div><div class="cmp-proscons-cons"><p><strong>Cons</strong></p><ul><li>Eleven v3 ranked 12th of 13 AI voices on Audio Realism Bench on 4 August 2026</li><li>The standard text to speech WebSocket doesn't accept Eleven v3 or v4</li></ul></div></div>

**Pricing:** $0.08 per 1,000 characters for Eleven v4, v3, and Multilingual v2, and $0.04 for v4 Turbo, v3 Conversational, and Flash, billed in dollars against plans from Free to Business at $990 a month.

### 7. Deepgram: Best for teams that want speech recognition and speech from one vendor that signs a BAA

**What does it do?** Deepgram sells speech recognition, text to speech, and a voice agent API, and says Flux TTS responds in as low as 80ms with mu-law at 8 kHz among its output formats.

<div class="cmp-proscons" data-rival="deepgram"><div class="cmp-proscons-pros"><p><strong>Pros</strong></p><ul><li>BAAs for Enterprise customers handling electronic protected health information</li><li>SOC 2 Type 1 and Type 2</li><li>Self-hosted and private cloud deployment for Flux TTS</li></ul></div><div class="cmp-proscons-cons"><p><strong>Cons</strong></p><ul><li>Its voices weren't in Audio Realism Bench's results of 4 August 2026</li><li>Flux TTS costs $0.045 per 1,000 characters on pay as you go</li></ul></div></div>

**Pricing:** $0.045 per 1,000 characters for Flux TTS, $0.030 for Aura-2, and $0.015 for Aura-1 on pay as you go.

## Which text to speech sounds most like a real person on a patient call?

In Design Arena's Audio Realism Bench results of 4 August 2026, Bland Speech v3 ranked first of 13 AI voices at 1365, behind only recorded human speech at 1500, ahead of Microsoft's MAI-Voice-2 at 1224, Google's Gemini 2.5 Pro TTS at 1109, and ElevenLabs' Eleven v3 at 938.

Design Arena plays listeners two unlabelled recordings of the same line and asks which sounds more like a real person, and a higher Elo rating means a voice was picked more often. Rime, Amazon Polly, and Deepgram weren't in those results, and ElevenLabs' Eleven v4, released on 28 September 2026, isn't scored in them. Design Arena [published the method and scores](https://notes.designarena.ai/audio-realism-benchmark-measuring-realism-in-audio-models/) on 4 August 2026.

## How were these text to speech APIs compared?

Samuel Oram-Jones compared seven APIs on how plainly each company's BAA covers speech, phone audio, voice realism, data handling, and price per character. Every rival detail comes from that company's own pricing, documentation, and trust pages, and voice scores come from Design Arena's published results of 4 August 2026.

Bland's [comparison of text to speech APIs](/compare/text-to-speech) covers the same vendors by job, the [best lists](/compare/text-to-speech/best-lists) group them by use, and best text to speech with 8 kHz phone audio goes deeper on phone formats.

## Frequently asked questions

### What is the best text to speech API for healthcare?

Bland Speech is the best text to speech API for healthcare calls in 2026 for teams that put voice quality on a phone line first. Bland Speech v3 ranked first of 13 AI voices on Audio Realism Bench on 4 August 2026, it returns mu-law at 8 kHz, and Bland is HIPAA compliant with a signed BAA.

### Which text to speech APIs sign a BAA?

Amazon, Google, Microsoft, Rime, Deepgram, ElevenLabs, and Bland all describe a BAA path. Amazon and Google tie it to Polly and Text-to-Speech by name, and Microsoft offers it through its Product Terms.

### Is Bland Speech HIPAA compliant?

Bland is HIPAA compliant with a signed BAA, and it is SOC 2 Type II audited. Bland is also FedRAMP 20x Class C certified at Moderate, granted on 17 November 2026, and Bland says speech synthesis runs inside its FedRAMP boundary.

### Can a clinic clone a staff member's voice for patient calls?

Bland Speech can. An instant clone needs one clean sample of about 10 seconds, and a professional clone is fine-tuned on 30 minutes or more of audio and goes through Bland's consent and rights review. Every clone is private to the customer's organization, and the customer confirms the voice is theirs to use.

### How much does text to speech cost for patient calls?

Prices run from $4 per million characters for Amazon Polly Standard voices to $100 per million for Polly Long-Form, and Bland Speech costs $40 per million, billed as $0.04 per 1,000 characters with no monthly plan.
