# Compare text to speech APIs (2026): Bland Speech, ElevenLabs, Cartesia, OpenAI, and more

Bland Speech is Bland's text to speech API, and it was built for phone calls. In Design Arena's blind listening test of 4 August 2026, Bland Speech v3 ranked first of 13 AI voices. It streams over HTTP or a WebSocket, starts speaking in about 199ms, returns the mu-law audio a phone line carries, and costs $0.04 per 1,000 characters. Its closest rivals are ElevenLabs, Cartesia, Microsoft Azure, Google, OpenAI, Deepgram, and Amazon Polly, and OpenAI retires its text to speech models on 6 January 2027.

## What a text to speech API does

A text to speech API takes words and gives back a voice reading them. A team with the whole script sends it over HTTP and gets a file back. A voice agent can't wait for the whole script, so it streams text into a WebSocket as its language model writes, and the voice starts talking before the sentence is finished.

Most of the APIs on this page sound good in a demo. They split on what happens after it: whether a stranger on the phone can tell the voice is synthetic, how long the caller sits in silence before the first word, and what a million characters cost once a team is in production. Phone audio is the one people forget. US phone networks carry mu-law at 8 kHz, and an API that can't produce it leaves a team converting every clip on the way out.

Bland Speech came out of Bland's phone agents. Bland builds and runs its own speech, language, and transcription models for enterprise calls, and on a call a voice that sounds too polished reads as fake, so this one keeps the breaths, the pauses, and the small stumbles people actually make.

## How Bland Speech sounds

These are Bland Speech v3 voices introducing themselves, exactly as the model rendered them. Karen, River, and the others are curated voices. David is an instant clone, made from a short sample of one person talking.

## Which voice sounds most like a person

Design Arena's Audio Realism Bench is a blind test. Listeners hear the same line read by two models, don't know which is which, and pick the one that sounds more like a real person. In the results Design Arena published on 4 August 2026, Bland Speech v3 came first of 13 AI voices with 1365. Recordings of actual people scored 1500, and that gap is what every model here is still chasing.

Deepgram and Amazon Polly weren't in the test. Some rivals have also shipped new models since, Cartesia's Sonic 3.6 and ElevenLabs' Eleven v4 among them, and those haven't been scored yet.

See [Design Arena's published results](https://notes.designarena.ai/audio-realism-benchmark-measuring-realism-in-audio-models/).

## What a month of speech costs

A million characters is roughly 20 hours of speech. At that volume Google's Chirp 3: HD costs nothing, because the first million each month are free, and Azure's Neural voices come to $15. Bland Speech is $40, the same as ElevenLabs' Eleven v4 Turbo, with Cartesia's plans close by.

Bland Speech isn't the cheapest voice here. The cheapest ones were built for announcements and alerts, where nobody minds a voice that sounds read out. On a call where someone has to trust what they're hearing, the gap between those voices and a human-sounding one is what a team is paying for.

## Twelve APIs, side by side

Each price is the company's own published rate, read on 17 and 18 November 2026. First-audio times are each company's own claim, timed its own way, so they say more about what a vendor promises than about what a caller will hear.

| API | Price per million characters | Free usage | First audio | Text in over a WebSocket | Mu-law at 8 kHz | Cloning | Audio Realism Bench, 4 August 2026 |
|---|---|---|---|---|---|---|---|
| Bland Speech (Bland Speech v3) | $40 | 50,000 characters, once | 199ms | Yes | Yes | Instant, and professional after a one-time $5 top-up | Bland Speech v3: #1, 1365 |
| ElevenLabs (Eleven v4 Turbo) | $40 to $80 | 10,000 v4 characters a month | About 100ms median | Yes | Yes | Instant from Starter, professional from Creator | Eleven v3: #12, 938 |
| Cartesia (Sonic 3.6) | $37.38 to $50 in a plan | 20,000 credits a month, personal use | Under 90ms | Yes | Yes | Instant from Pro, professional from Startup | Sonic 3.5: #6, 1096 |
| Microsoft Azure (Neural and Neural HD Flash) | $15 | 0.5 million characters a month | Under 300ms | Yes | Yes | Limited access | MAI-Voice-2: #2, 1224 |
| Google (Chirp 3: HD) | $30 | 1 million characters a month | Not published | Through client libraries | Yes | Closed to new requests on Chirp 3 | Gemini 2.5 Pro TTS: #5, 1109 |
| OpenAI (tts-1 and tts-1-hd) | $15 and $30 | None | Not published | Realtime API only | No | Eligible customers only | GPT Realtime 2: #4, 1119 |
| Deepgram (Flux TTS and Aura-2) | $45 and $30 | $200 of credit | As low as 80ms | Yes | Yes | Through sales | Not in these results |
| Amazon Polly (Generative, Neural, and Standard) | $30, $16, and $4 | First 12 months | Not published | HTTP/2 stream on Generative | Yes | Through AWS, as Brand Voice | Not in these results |
| Grok TTS (Grok Text to Speech) | $15 | Not published | Not published | Yes | Yes | Instant from a clip, API access on Enterprise | Grok TTS: #3, 1156 |
| MiniMax (Speech 2.8 HD and Turbo) | $100 and $60 | Not published | Not published | Yes | Yes | Instant from 10 seconds, $1.50 a voice | Speech-02 HD: #7, 1093 |
| Smallest AI (Lightning v3.1 Pro) | $19.50 | $10 in credits | Under 100ms | Yes | Yes | Instant from 5 to 15 seconds, professional on Enterprise | Lightning v3.1 Pro: #11, 952 |
| Inworld (Realtime TTS-2 and TTS-2 Flash) | $25 and $15 | Up to 70 minutes on the $0 plan | As low as 20ms | Yes | Yes | Instant from 3 seconds, professional in beta | TTS-1.5 Max: #13, 763 |

## Which API fits the job

### Phone calls and voice agents

Bland Speech fits calls where the person on the line should hear a person. It ranked first on Audio Realism Bench on 4 August 2026, returns mu-law for phone lines, and is the voice on Bland's own enterprise phone agents. See [Hear Bland Speech](/speech).

### Moving off OpenAI

OpenAI's tts-1, tts-1-hd, and gpt-4o-mini-tts shut down on 6 January 2027, and their replacement runs on the Realtime API instead of /v1/audio/speech. Bland Speech's POST /v2/audio/speech implements the same contract, so a team keeps its OpenAI SDK and changes the base URL, the key, and the model name to btts-3. See [See the API](/text-to-speech-api).

### Cloning a brand voice

Bland Speech makes an instant clone from about 10 seconds of audio and a professional clone from 30 minutes or more, after a one-time $5 top-up, with no monthly plan. ElevenLabs clones from its Starter and Creator plans, and Cartesia from its Pro and Startup plans. See [Voice cloning comparisons](/compare/text-to-speech/voice-cloning).

### Many languages from one vendor

ElevenLabs lists 90+ languages on its Eleven v4 family, Azure 100+ languages and locales on its standard voices, and Cartesia 44 on Sonic 3.6. A team voicing many markets should start with those three and listen in each language it needs.

### Announcements at volume

Amazon Polly Standard and Google WaveNet and Standard voices cost $4 per million characters, and Azure Neural voices $15. They suit recorded announcements, alerts, and reading content aloud, where cost per character matters more than a voice that passes as human.

### Running the model itself

Cartesia offers on-premise, air-gapped, and VPC deployment under enterprise contracts, and Deepgram offers self-hosted and private cloud deployment for Flux TTS. A security team that must operate the model itself should compare those two.

## Providers that shut down

Text to speech has already lost providers. A team that built on one of them has to rewrite its integration and rebuild its voices, because a cloned voice doesn't transfer from one provider to another. The original recordings are the thing worth keeping.

### OpenAI TTS: shutting down (6 January 2027)

OpenAI's documentation lists tts-1, tts-1-hd, and gpt-4o-mini-tts as deprecated and points to gpt-realtime-2.1-mini on its Realtime API. Bland Speech's OpenAI-compatible endpoint keeps the same request code.

### Hume: no text to speech api listed (As of 17 November 2026)

Hume's website and developer documentation list audio analysis APIs and no text to speech or voice API. A team that built on Hume's Octave voices needs a new provider and new clones.

### LMNT: shut down (No date given)

LMNT's website says "LMNT has shut down". Its customers need a new streaming text to speech provider.

### PlayHT: site offline (As of 17 November 2026)

The play.ht site no longer loads. A team with PlayHT voices in production needs a new provider and its original recordings.

## Every comparison

Every text to speech comparison Bland publishes, grouped by the question it answers: one rival against Bland Speech, where to go after a provider, what a product is really like, two rivals against each other, the best options for a job, voice cloning, and guides.

### [Bland Speech vs every text to speech API](/compare/text-to-speech/head-to-heads)

Bland Speech set against one rival at a time on voice realism, price per character, streaming, phone audio, and cloning.

- [Bland Speech vs Cartesia (2026): Which text to speech API suits a voice agent?](/compare/bland-speech-vs-cartesia)
- [Bland Speech vs ElevenLabs (2026): Which text to speech API fits a phone line?](/compare/bland-speech-vs-elevenlabs)
- [Bland Speech vs OpenAI TTS (2026): What to use before OpenAI's January 2027 shutdown](/compare/bland-speech-vs-openai-tts)
- [Bland Speech vs Google text to speech (2026): Chirp 3, Gemini, and one flat rate](/compare/bland-speech-vs-google-tts)
- [Bland Speech vs Azure text to speech (2026): Neural voices, MAI-Voice, and phone audio](/compare/bland-speech-vs-azure-tts)
- [Bland Speech vs Amazon Polly (2026): Is a cheaper voice worth it on a phone call?](/compare/bland-speech-vs-amazon-polly)
- [Bland Speech vs Deepgram Aura (2026): Flux TTS, Aura-2, and a voice for phone calls](/compare/bland-speech-vs-deepgram)
- [Bland Speech vs MiniMax (2026): Which text to speech API sounds more human on a call?](/compare/bland-speech-vs-minimax)
- [Bland Speech vs Inworld (2026): Which text to speech API is better for phone agents?](/compare/bland-speech-vs-inworld)
- [Bland Speech vs Speechify (2026): Which text to speech API is better for voice agents?](/compare/bland-speech-vs-speechify)
- [Bland Speech vs Murf (2026): Which text to speech API is worth the higher price?](/compare/bland-speech-vs-murf)
- [Bland Speech vs Fish Audio (2026): Which text to speech API is better for phone calls?](/compare/bland-speech-vs-fish-audio)
- [Bland Speech vs Rime (2026): Which text to speech API is better for voice agents?](/compare/bland-speech-vs-rime)
- [Bland Speech vs Resemble AI (2026): Does Resemble AI still sell text to speech?](/compare/bland-speech-vs-resemble-ai)
- [Bland Speech vs WellSaid (2026): Voiceover studio or text to speech API for live calls?](/compare/bland-speech-vs-wellsaid)
- [Bland Speech vs Smallest AI (2026): Is a cheaper text to speech API good enough for a phone call?](/compare/bland-speech-vs-smallest-ai)
- [Bland Speech vs Grok TTS (2026): What a $25 per million price gap buys on a phone call](/compare/bland-speech-vs-grok-tts)
- [Bland Speech vs Mistral Voxtral TTS (2026): A model in Public Preview against one built for phone calls](/compare/bland-speech-vs-voxtral-tts)
- [Bland Speech vs Qwen TTS (2026): Pay per character, or run Alibaba's open model on a team's own GPUs](/compare/bland-speech-vs-qwen-tts)
- [Bland Speech vs NVIDIA Riva (2026): An API a team calls or a container on its own GPUs](/compare/bland-speech-vs-nvidia-riva)
- [Bland Speech vs Gradium (2026): A first-audio claim of under 50ms against a voice built for phone calls](/compare/bland-speech-vs-gradium)
- [Bland Speech vs Sarvam (2026): Which text to speech API suits a voice agent?](/compare/bland-speech-vs-sarvam)
- [Bland Speech vs Lovo (2026): What changed at Lovo and what to use instead](/compare/bland-speech-vs-lovo)
- [Bland Speech vs Typecast (2026): Which text to speech API suits a phone agent?](/compare/bland-speech-vs-typecast)
- [Bland Speech vs Unreal Speech (2026): What does a higher price per character buy?](/compare/bland-speech-vs-unreal-speech)
- [Bland Speech vs IBM Watson text to speech (2026): Which is better for a contact center voice agent?](/compare/bland-speech-vs-ibm-watson-tts)
- [Bland Speech vs ReadSpeaker (2026): Which text to speech API suits a phone agent?](/compare/bland-speech-vs-readspeaker)
- [Bland Speech vs Speechmatics (2026): Can a text to speech API still in preview carry a phone line?](/compare/bland-speech-vs-speechmatics)
- [Bland Speech vs Neuphonic (2026): Which text to speech API is easier to put in a budget?](/compare/bland-speech-vs-neuphonic)
- [Bland Speech vs Respeecher (2026): Can a team make its own voice on a text to speech API?](/compare/bland-speech-vs-respeecher)
- [Bland Speech vs Kokoro (2026): Is a free open-weight model or a hosted API better for phone calls?](/compare/bland-speech-vs-kokoro)
- [Bland Speech vs Chatterbox (2026): Is retired open-source Chatterbox still worth hosting for phone calls?](/compare/bland-speech-vs-chatterbox)
- [Bland Speech vs Orpheus TTS (2026): What does it take to run Orpheus for phone calls?](/compare/bland-speech-vs-orpheus-tts)

### [Text to speech alternatives](/compare/text-to-speech/alternatives)

Where to go from each text to speech provider, including the ones that shut down or are shutting down.

- [6 OpenAI TTS alternatives in 2026 before the 6 January 2027 shutdown](/blog/openai-tts-alternatives)
- [5 Hume Octave alternatives in 2026 for expressive text to speech](/blog/hume-tts-alternatives)
- [5 PlayHT alternatives in 2026 for teams whose PlayHT API stopped answering](/blog/playht-alternatives)
- [6 LMNT alternatives in 2026 now that LMNT has shut down](/blog/lmnt-alternatives)
- [5 Coqui alternatives in 2026 for teams that built on XTTS-v2](/blog/coqui-alternatives)
- [5 Cartesia alternatives in 2026 for voice agents that outgrow a credit plan](/blog/cartesia-alternatives)
- [5 Google text to speech alternatives in 2026 for teams that need a custom voice](/blog/google-text-to-speech-alternatives)
- [6 Amazon Polly alternatives in 2026 for cloned voices and live calls](/blog/amazon-polly-alternatives)
- [6 Azure text to speech alternatives in 2026 for production voice agents](/blog/azure-text-to-speech-alternatives)
- [5 Deepgram Aura alternatives in 2026 for low-latency voice agents](/blog/deepgram-aura-alternatives)
- [5 Murf alternatives in 2026 for cloned voices and phone calls](/blog/murf-alternatives)
- [5 Speechify API alternatives in 2026 for voice agents and phone calls](/blog/speechify-api-alternatives)
- [5 WellSaid alternatives in 2026 for voiceover, narration, and phone calls](/blog/wellsaid-alternatives)
- [5 Resemble AI alternatives in 2026 after it stopped selling text to speech](/blog/resemble-ai-alternatives)
- [5 MiniMax speech alternatives in 2026 for cloned voices and phone calls](/blog/minimax-speech-alternatives)
- [5 Inworld TTS alternatives in 2026 for live voice agents](/blog/inworld-tts-alternatives)
- [6 Fish Audio alternatives in 2026 for text to speech on a phone line](/blog/fish-audio-alternatives)
- [5 Rime alternatives in 2026 for voice agents on a phone line](/blog/rime-alternatives)
- [6 Smallest AI alternatives in 2026, before lightning_v3.1 retires](/blog/smallest-ai-alternatives)
- [5 Lovo alternatives in 2026 now that Lovo's site is offline](/blog/lovo-alternatives)
- [5 Typecast alternatives in 2026 for phone calls and voice agents](/blog/typecast-alternatives)
- [5 Unreal Speech alternatives in 2026 for voices that hold up on a call](/blog/unreal-speech-alternatives)
- [5 Sarvam alternatives in 2026 for phone calls billed in dollars](/blog/sarvam-alternatives)
- [5 Gradium alternatives in 2026 for voice agents on live phone calls](/blog/gradium-alternatives)
- [5 IBM Watson text to speech alternatives in 2026 for streaming voice agents](/blog/ibm-watson-tts-alternatives)
- [6 NVIDIA Riva alternatives in 2026 for text to speech on phone calls](/blog/nvidia-riva-alternatives)

### [Text to speech API reviews](/compare/text-to-speech/reviews)

What each text to speech API is, how it works, what it costs, and why enterprises choose Bland Speech.

- [Cartesia review (2026): What it is and why enterprises choose Bland Speech](/blog/cartesia-review)
- [Deepgram Aura review (2026): What it is and why enterprises choose Bland Speech](/blog/deepgram-aura-review)
- [Google text to speech review (2026): What it is and why enterprises choose Bland Speech](/blog/google-text-to-speech-review)
- [Azure text to speech review (2026): What it is and why enterprises choose Bland Speech](/blog/azure-text-to-speech-review)
- [Amazon Polly review (2026): What it is and why enterprises choose Bland Speech](/blog/amazon-polly-review)
- [Murf AI review (2026): What it is and why enterprises choose Bland Speech](/blog/murf-ai-review)
- [Speechify API review (2026): What it is and why enterprises choose Bland Speech](/blog/speechify-api-review)
- [Inworld TTS review (2026): What it is and why enterprises choose Bland Speech](/blog/inworld-tts-review)
- [MiniMax speech review (2026): What it is and why enterprises choose Bland Speech](/blog/minimax-speech-review)
- [Rime review (2026): What it is and why enterprises choose Bland Speech](/blog/rime-review)
- [Fish Audio review (2026): What it is and why enterprises choose Bland Speech](/blog/fish-audio-review)
- [Resemble AI review (2026): What it is and why enterprises choose Bland Speech](/blog/resemble-ai-review)
- [WellSaid review (2026): What it is and why enterprises choose Bland Speech](/blog/wellsaid-review)
- [Smallest AI review (2026): What it is and why enterprises choose Bland Speech](/blog/smallest-ai-review)
- [Gradium review (2026): What it is and why enterprises choose Bland Speech](/blog/gradium-review)
- [Sarvam review (2026): What it is and why enterprises choose Bland Speech](/blog/sarvam-review)
- [Unreal Speech review (2026): What it is and why enterprises choose Bland Speech](/blog/unreal-speech-review)

### [Text to speech rivals compared](/compare/text-to-speech/rival-vs-rival)

Two or more rivals compared on the question buyers ask, with where Bland Speech fits.

- [ElevenLabs vs Cartesia (2026): Which text to speech API holds up on a phone call?](/blog/elevenlabs-vs-cartesia)
- [ElevenLabs vs OpenAI TTS (2026): What a shutdown date does to the choice](/blog/elevenlabs-vs-openai-tts)
- [Google text to speech vs Amazon Polly (2026): Same $4 price, different voices](/blog/google-text-to-speech-vs-amazon-polly)
- [ElevenLabs vs Google text to speech (2026): Who sells a cloned voice today?](/blog/elevenlabs-vs-google-text-to-speech)
- [Cartesia vs Deepgram Aura (2026): Aura is no longer the Deepgram model to compare](/blog/cartesia-vs-deepgram-aura)
- [Azure text to speech vs Google text to speech (2026): Which cloud voice suits a phone call?](/blog/azure-text-to-speech-vs-google-text-to-speech)
- [Azure text to speech vs Amazon Polly (2026): Which cloud API costs less for a voice agent?](/blog/azure-text-to-speech-vs-amazon-polly)
- [ElevenLabs vs Murf (2026): Which text to speech API fits a voice agent budget?](/blog/elevenlabs-vs-murf)
- [ElevenLabs vs Speechify (2026): Which text to speech API costs less at volume?](/blog/elevenlabs-vs-speechify)
- [ElevenLabs vs Deepgram Aura (2026): Which text to speech API suits a voice agent?](/blog/elevenlabs-vs-deepgram-aura)
- [ElevenLabs vs Inworld (2026): Which text to speech API fits a voice agent?](/blog/elevenlabs-vs-inworld)
- [ElevenLabs vs MiniMax (2026): Which text to speech API costs less to run?](/blog/elevenlabs-vs-minimax)
- [ElevenLabs vs Resemble AI (2026): Is Resemble still an option for text to speech?](/blog/elevenlabs-vs-resemble-ai)
- [ElevenLabs vs Fish Audio (2026): Which text to speech API is cheaper to run?](/blog/elevenlabs-vs-fish-audio)
- [ElevenLabs vs WellSaid (2026): Which AI voice fits a team that produces narration?](/blog/elevenlabs-vs-wellsaid)
- [ElevenLabs vs Amazon Polly (2026): A $4 voice or an $80 one?](/blog/elevenlabs-vs-amazon-polly)
- [OpenAI TTS vs Google text to speech (2026): Which endpoint is safe to build on?](/blog/openai-tts-vs-google-text-to-speech)
- [OpenAI TTS vs Azure text to speech (2026): Which one outputs phone-line audio?](/blog/openai-tts-vs-azure-text-to-speech)
- [Cartesia vs OpenAI TTS (2026): A monthly allowance or a bill per character?](/blog/cartesia-vs-openai-tts)
- [Cartesia vs Inworld (2026): Two latency claims, measured two different ways](/blog/cartesia-vs-inworld)
- [Cartesia vs MiniMax (2026): Which text to speech API fits a voice agent?](/blog/cartesia-vs-minimax)
- [Cartesia vs Rime (2026): Which latency number can a phone agent plan around?](/blog/cartesia-vs-rime)
- [Cartesia vs Smallest AI (2026): Cheaper per character or better sounding?](/blog/cartesia-vs-smallest-ai)
- [Deepgram Aura vs Rime (2026): Per character or per minute, which costs less?](/blog/deepgram-aura-vs-rime)
- [Inworld vs MiniMax (2026): Which text to speech API is worth the price?](/blog/inworld-vs-minimax)
- [Fish Audio vs MiniMax (2026): Which text to speech API fits a voice agent on a phone line?](/blog/fish-audio-vs-minimax)
- [Murf vs WellSaid (2026): Which text to speech platform suits an app, and which suits a voiceover team?](/blog/murf-vs-wellsaid)
- [Murf vs Speechify (2026): Which text to speech API costs less per million characters?](/blog/murf-vs-speechify)
- [Resemble AI vs WellSaid (2026): Can a new customer still buy text to speech from Resemble AI?](/blog/resemble-ai-vs-wellsaid)
- [Kokoro vs Chatterbox (2026): Which open-weight text to speech model is still worth hosting?](/blog/kokoro-vs-chatterbox)
- [Bland Speech vs ElevenLabs vs Cartesia (2026): Which text to speech API fits a phone line?](/blog/bland-speech-vs-elevenlabs-vs-cartesia)
- [Bland Speech vs OpenAI vs Google vs Azure text to speech (2026): Which one should a voice agent use?](/blog/bland-speech-vs-openai-vs-google-vs-azure-tts)
- [Cloud text to speech compared in 2026: Amazon Polly, Google, Azure, and Bland Speech](/blog/cloud-text-to-speech-compared)
- [Voice agent text to speech in 2026: Deepgram, Cartesia, ElevenLabs, and Bland Speech](/blog/voice-agent-tts-compared)
- [Phone call voices in 2026: Bland Speech vs Deepgram vs Rime](/blog/bland-speech-vs-deepgram-vs-rime)
- [Inworld vs MiniMax vs Fish Audio vs Bland Speech (2026): Which text to speech API holds up on a phone call?](/blog/inworld-vs-minimax-vs-fish-audio-vs-bland-speech)
- [ElevenLabs vs Murf vs WellSaid vs Speechify (2026): Which voiceover tool fits a team?](/blog/elevenlabs-vs-murf-vs-wellsaid-vs-speechify)
- [Open-source text to speech compared (2026): Kokoro, Chatterbox, Orpheus, and Bland Speech](/blog/open-source-tts-compared)

### [The best text to speech APIs, by job](/compare/text-to-speech/best-lists)

Ranked lists by voice quality, speed, phone and voice agent work, industry, and buying needs.

- [8 best text to speech APIs for business in 2026](/blog/best-text-to-speech-apis-2026)
- [7 most expressive text to speech APIs in 2026](/blog/most-expressive-tts-apis)
- [6 best text to speech APIs with emotion control in 2026](/blog/best-tts-emotion-control)
- [7 best text to speech APIs with audio and performance tags in 2026](/blog/best-tts-performance-tags)
- [6 most human-sounding AI voices for phone calls in 2026](/blog/most-human-sounding-ai-voices-phone)
- [7 most natural-sounding text to speech APIs in 2026](/blog/most-natural-sounding-tts)
- [6 best AI voices for customer conversations in 2026](/blog/best-ai-voices-customer-conversations)
- [6 best text to speech APIs for directing a voice performance in 2026](/blog/best-tts-voice-direction)
- [6 best conversational text to speech models in 2026](/blog/best-conversational-tts-models)
- [6 best text to speech APIs for an expressive brand voice in 2026](/blog/best-tts-expressive-brand-voice)
- [6 best streaming text to speech APIs in 2026](/blog/best-streaming-tts-apis)
- [6 best real-time text to speech APIs in 2026](/blog/best-real-time-tts-apis)
- [6 best WebSocket text to speech APIs in 2026](/blog/best-websocket-tts-apis)
- [6 best text to speech APIs for streaming LLM output in 2026](/blog/best-tts-for-llm-streaming)
- [5 best text to speech APIs that handle interruptions in 2026](/blog/best-tts-interruptions-barge-in)
- [7 best text to speech APIs for phone calls in 2026, compared](/blog/best-tts-for-phone-calls)
- [6 best text to speech APIs for voice agents in 2026, compared](/blog/best-tts-for-voice-agents)
- [6 best text to speech APIs for conversational AI in 2026, compared](/blog/best-tts-for-conversational-ai)
- [6 best text to speech APIs for IVR in 2026, compared](/blog/best-tts-for-ivr)
- [6 best text to speech APIs for call centers in 2026, compared](/blog/best-tts-for-call-centers)
- [6 best text to speech APIs for AI receptionists in 2026](/blog/best-tts-for-ai-receptionists)
- [6 best text to speech APIs for outbound calling in 2026](/blog/best-tts-for-outbound-calls)
- [6 best text to speech APIs for customer service in 2026](/blog/best-tts-for-customer-service)
- [6 best text to speech services for Pipecat in 2026](/blog/best-tts-for-pipecat)
- [6 best text to speech providers for LiveKit agents in 2026](/blog/best-tts-for-livekit)
- [7 best text to speech APIs for healthcare calls in 2026](/blog/best-tts-for-healthcare)
- [6 best text to speech APIs for banks and financial services in 2026](/blog/best-tts-for-financial-services)
- [6 best text to speech APIs for insurance in 2026](/blog/best-tts-for-insurance)
- [6 best text to speech APIs for debt collection calls in 2026](/blog/best-tts-for-collections)
- [6 best text to speech APIs for appointment reminders in 2026](/blog/best-tts-for-appointment-reminders)
- [6 best text to speech APIs for sales calls in 2026](/blog/best-tts-for-sales-calls)
- [7 best text to speech APIs for hospitality and restaurants in 2026](/blog/best-tts-for-hospitality)
- [6 best text to speech APIs for real estate in 2026](/blog/best-tts-for-real-estate)
- [7 best text to speech APIs for logistics and delivery updates in 2026](/blog/best-tts-for-logistics)
- [7 best text to speech APIs for utilities and telecom in 2026](/blog/best-tts-for-utilities-telecom)
- [7 best text to speech APIs for government services in 2026](/blog/best-tts-for-government)
- [7 best text to speech APIs for e-commerce support calls in 2026](/blog/best-tts-for-ecommerce)
- [8 best enterprise text to speech platforms in 2026, compared](/blog/best-enterprise-tts)
- [7 best text to speech APIs for developers in 2026, compared](/blog/best-tts-apis-for-developers)
- [7 best pay-per-use text to speech APIs in 2026, compared](/blog/best-pay-as-you-go-tts)
- [6 best text to speech APIs without a monthly subscription in 2026](/blog/best-tts-no-subscription)
- [6 best text to speech APIs for startups in 2026](/blog/best-tts-for-startups)

### [Voice cloning APIs compared](/compare/text-to-speech/voice-cloning)

Cloning lists, head-to-heads, alternatives, and guides: how much audio a clone needs, what consent each provider asks for, and what it costs.

- [6 best voice cloning APIs in 2026, compared by audio needed and price](/blog/best-voice-cloning-apis)
- [6 best instant voice cloning APIs in 2026, from 3 seconds of audio](/blog/best-instant-voice-cloning-apis)
- [6 best professional voice cloning services for brands in 2026](/blog/best-professional-voice-cloning)
- [6 best voice cloning services for phone calls in 2026](/blog/best-voice-cloning-for-phone-calls)
- [6 best voice cloning APIs for voice agents in 2026](/blog/best-voice-cloning-for-voice-agents)
- [6 best voice cloning services for business in 2026, compared on consent and rights](/blog/best-voice-cloning-for-business)
- [6 best voice cloning tools from 10 seconds of audio in 2026](/blog/best-voice-cloning-10-seconds)
- [6 best real-time voice cloning APIs in 2026, compared on streaming and first audio](/blog/best-real-time-voice-cloning)
- [6 best voice cloning services for call centers in 2026, compared on phone audio and paperwork](/blog/best-voice-cloning-for-call-centers)
- [6 best voice cloning services for customer service in 2026](/blog/best-voice-cloning-for-customer-service)
- [6 best voice cloning services for sales calls in 2026](/blog/best-voice-cloning-for-sales-calls)
- [6 best voice cloning services with no monthly subscription in 2026](/blog/best-voice-cloning-no-subscription)
- [6 best text to speech services for custom brand voices in 2026](/blog/best-tts-custom-brand-voices)
- [6 best expressive voice cloning APIs in 2026, ranked by what a clone keeps from its recording](/blog/best-expressive-voice-cloning)
- [Bland Speech vs ElevenLabs voice cloning (2026): Which cloning API suits a phone line?](/compare/bland-speech-vs-elevenlabs-voice-cloning)
- [Bland Speech vs Cartesia voice cloning (2026): How the two clone a voice for calls](/compare/bland-speech-vs-cartesia-voice-cloning)
- [Bland Speech vs Resemble AI voice cloning (2026): What changed and where to clone a voice now](/compare/bland-speech-vs-resemble-ai-voice-cloning)
- [Bland Speech vs Azure custom voice cloning (2026): Access, consent, and hosting costs compared](/compare/bland-speech-vs-azure-custom-voice-cloning)
- [Bland Speech vs Google instant custom voice cloning (2026): What is still open to a new team](/compare/bland-speech-vs-google-custom-voice-cloning)
- [Bland Speech vs Respeecher voice cloning (2026): Which clones a voice a developer can call?](/compare/bland-speech-vs-respeecher-voice-cloning)
- [Bland Speech vs Speechify voice cloning (2026): Is a cheaper clone the better clone?](/compare/bland-speech-vs-speechify-voice-cloning)
- [Bland Speech vs Fish Audio voice cloning (2026): Who else gets to use a cloned voice?](/compare/bland-speech-vs-fish-audio-voice-cloning)
- [Bland Speech vs MiniMax voice cloning (2026): What happens to a cloned voice after it is made?](/compare/bland-speech-vs-minimax-voice-cloning)
- [Bland Speech vs Murf voice cloning (2026): Which plan actually lets a developer clone a voice?](/compare/bland-speech-vs-murf-voice-cloning)
- [6 ElevenLabs voice cloning alternatives in 2026](/blog/elevenlabs-voice-cloning-alternatives)
- [5 Respeecher alternatives in 2026 for cloning a voice through an API](/blog/respeecher-alternatives)
- [5 Descript Overdub alternatives in 2026 now that Overdub is Regenerate](/blog/descript-overdub-alternatives)
- [Instant vs professional voice cloning (2026): Which a business needs](/blog/instant-vs-professional-voice-cloning)
- [How much audio does it take to clone a voice in 2026?](/blog/how-much-audio-to-clone-a-voice)
- [Is voice cloning legal for business in 2026? Consent rules by provider](/blog/is-voice-cloning-legal)
- [Cloned voice vs stock voice for a phone agent (2026)](/blog/cloned-vs-stock-voice-phone-agent)
- [How voice cloning works (2026): From a recording to a voice](/blog/how-voice-cloning-works)
- [Voice cloning API pricing in 2026, compared](/blog/voice-cloning-api-pricing)
- [How to move a cloned voice to Bland Speech (2026)](/blog/move-cloned-voice-to-bland-speech)

### [Text to speech guides](/compare/text-to-speech/guides)

Migration guides, pricing explainers, and how text to speech works on a phone call, from latency and streaming to phone audio formats.

- [How to migrate from OpenAI TTS to Bland Speech (2026): Three changed values, and what doesn't carry over](/blog/migrate-from-openai-tts)
- [How to migrate from Hume Octave to Bland Speech (2026): What Hume's site shows, and a plan for the move](/blog/migrate-from-hume-tts)
- [How to migrate from PlayHT to Bland Speech (2026): Moving an integration when PlayHT's API no longer answers](/blog/migrate-from-playht)
- [How to migrate from ElevenLabs text to speech to Bland Speech (2026): Streaming, voices, and billing](/blog/migrate-from-elevenlabs-tts)
- [How to migrate from Cartesia to Bland Speech (2026): Contexts, credits, and 8 kHz audio](/blog/migrate-from-cartesia)
- [How to migrate from Google text to speech to Bland Speech (2026): What maps, what changes, and what can't move](/blog/migrate-from-google-tts)
- [How to migrate from Azure text to speech to Bland Speech (2026): SSML, voices, and cost](/blog/migrate-from-azure-tts)
- [How to migrate from Amazon Polly to Bland Speech (2026): Engines, 8 kHz audio, and what the bill does](/blog/migrate-from-amazon-polly)
- [Text to speech API pricing in 2026, compared](/blog/text-to-speech-api-pricing)
- [What an hour of AI speech costs in 2026, by provider](/blog/ai-speech-cost-per-hour)
- [Per-character vs credit vs token pricing for text to speech in 2026](/blog/tts-pricing-models-explained)
- [Open-source text to speech vs a hosted API (2026): Where Bland Speech fits](/blog/open-source-tts-vs-hosted-api)
- [Time to first audio (2026): How text to speech latency is measured and where Bland Speech stands](/blog/tts-latency-explained)
- [Mu-law vs PCM (2026): Which audio format a phone call needs from Bland Speech and other text to speech APIs](/blog/mu-law-vs-pcm-tts)
- [SSML vs performance tags (2026): Two ways to direct a text to speech voice, and what Bland Speech uses](/blog/ssml-vs-performance-tags)
- [What makes an AI voice expressive? Tags, prompts, and controls in 2026](/blog/what-makes-ai-voice-expressive)
- [Streaming text to speech over a WebSocket, explained (2026)](/blog/streaming-tts-websocket)
- [How to choose a voice for a phone agent in 2026](/blog/choose-voice-for-phone-agent)
- [8 kHz vs 48 kHz in 2026: what sample rate a text to speech voice needs](/blog/tts-sample-rates-explained)
- [Why text to speech providers shut down, and how to avoid getting stranded (2026)](/blog/tts-provider-shutdowns)
- [Text to speech vs speech-to-speech for voice agents (2026): What a phone call needs from a voice](/blog/tts-vs-speech-to-speech)

## Beyond text to speech

Bland Speech is one part of Bland. The pages below cover the rest, from the studio to the phone agents this voice was built for.

- [Bland Speech studio](/speech): Type any line and hear Bland Speech read it, direct the performance with tags, and clone a voice from a short sample.
- [Text to speech API](/text-to-speech-api): Streaming over HTTP and WebSocket, the OpenAI-compatible endpoint, and code for a first call.
- [Realistic text to speech](/realistic-text-to-speech): The benchmark behind the ranking, and how Bland Speech keeps the pauses and breaths that make a voice sound human.
- [Tofu-1 speech to speech](/speech-to-speech): Bland's full duplex speech-to-speech model for enterprise phone calls, which listens while it speaks.
- [AI voice agents](/ai-voice-agents): How Bland's voice agents answer, qualify, and resolve phone calls end to end.
- [AI phone number](/ai-phone-number): A US number an AI agent can call and text from, $9.99 for the first month and then $19.99 a month, with fair-use limits.
- [Voice agent comparisons](/compare): Bland against Retell, Vapi, ElevenLabs, and other voice agent platforms for enterprise calls.

## Frequently asked questions

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

Bland Speech is the best text to speech API for business calls and voice agents as of November 2026. Bland Speech v3 ranked first of 13 AI voices on Audio Realism Bench on 4 August 2026, it returns phone-ready mu-law audio, and it costs $0.04 per 1,000 characters.

### What is the most realistic text to speech?

Bland Speech. In Design Arena's Audio Realism Bench results of 4 August 2026, Bland Speech v3 ranked first among 13 AI voices at 1365, ahead of Microsoft's MAI-Voice-2 at 1224, and only real human recordings scored higher.

### How much does a text to speech API cost?

Between $4 and $100 per million characters, depending on the vendor and the voice. Bland Speech costs $40 per million with no plan, ElevenLabs $40 or $80 by model, Google Chirp 3: HD $30, Azure Neural $15, and Amazon Polly Standard $4.

### What is the fastest text to speech API?

Each company publishes its own figure. Deepgram says Flux TTS starts in as low as 80ms, Cartesia under 90ms, ElevenLabs about 100ms at the median for v4 Turbo, Bland Speech 199ms, and Azure under 300ms for its standard and HD voices. Smallest AI says under 100ms, and Inworld says TTS-2 Flash starts in as low as 50ms.

### Is OpenAI shutting down its text to speech models?

Yes. OpenAI has deprecated tts-1, tts-1-hd, and gpt-4o-mini-tts, which shut down on 6 January 2027. Bland Speech's POST /v2/audio/speech implements the same contract, so a team can switch by changing its base URL, key, and model.

### Which text to speech API works best for phone calls?

Bland Speech, because Bland built it for phone calls, it ranked first on Audio Realism Bench on 4 August 2026, and it returns mu-law at 8 kHz. ElevenLabs, Cartesia, Azure, Google, Deepgram, Amazon Polly, Grok TTS, MiniMax, Smallest AI, and Inworld also return mu-law, and OpenAI's speech endpoint doesn't.

### Is Bland Speech HIPAA compliant?

Bland is HIPAA compliant, with a BAA on its Enterprise plan, and its trust page covers its text to speech along with its voice, transcription, and language models, all operated by Bland.
