---
title: "Text to Speech Providers for a Voice Agent | Micdrop"
description: "The text to speech providers Micdrop integrates with, hosted or running locally in Node.js, compared on latency, quality, voices and price per hour."
url: "https://micdrop.dev/docs/text-to-speech"
---

# Text to Speech Providers for a Voice Agent

The text to speech reads the answers of the agent while they are written, so the user hears the first sentence before the last one exists. It is passed to the server as `tts`.

## Hosted

*   **[ElevenLabs](/docs/text-to-speech/elevenlabs)**, high-quality voice synthesis, with audio tags on Eleven v4 Turbo
*   **[Cartesia](/docs/text-to-speech/cartesia)**, low-latency streaming TTS
*   **[Gemini TTS](/docs/text-to-speech/gemini)**, 30 voices, directed with plain instructions
*   **[Mistral Voxtral Speech](/docs/text-to-speech/mistral)**, Voxtral Speech 3 in 35+ languages, with voice cloning
*   **[OpenAI](/docs/text-to-speech/openai)**, `gpt-realtime-2.1-mini` or the speech endpoint models
*   **[Gradium](/docs/text-to-speech/gradium)**, streaming voices on an EU endpoint

## Local

*   **[Kokoro](/docs/text-to-speech/kokoro)**, in your Node process, English only
*   **[Phonon](/docs/text-to-speech/phonon)**, by Gradium, in your Node process, five languages
*   **[Piper](/docs/text-to-speech/piper)**, 53 languages
*   **[Pocket TTS](/docs/text-to-speech/pocket-tts)**, voice cloning in your Node process, English only
*   **[Qwen3-TTS](/docs/text-to-speech/qwen-tts)**, ten languages, on an mlx-audio server

The [local text to speech guide](/docs/local-models/text-to-speech) helps pick a model.

## Comparison

Provider

Latency

Quality

Voices

Cost per hour

Best For

**ElevenLabs**

~400ms

Excellent

1000+

$1.80 (Flash v2.5), $3.60 (Multilingual v2)

High-quality voices

**ElevenLabs v4 Turbo**

~100ms

Excellent

1000+

$1.80

Expressive voices, audio tags

**Cartesia**

~150ms

Good

50+

$1.80

Low-latency streaming

**Gradium 🇫🇷**

~300ms

Excellent

150+

$2.60

French, EU data residency

**Kokoro (local)**

~1000ms

Good

28

Free

Privacy, English only

**Phonon (local) 🇫🇷**

~50ms

Very good

102

Free

Privacy, five languages

**Piper (local)**

~390ms

Fair

178

Free

Privacy, 53 languages

**Qwen3-TTS (local)**

~400ms

Very good

9

Free

Privacy, ten languages

Costs are the published list price of the entry paid plan in August 2026, per hour of audio generated. [ElevenLabs bills its API in dollars](/blog/elevenlabs-api-pricing-voice-agent) at the same price on every plan, $40 per million characters on Eleven v4 Turbo and Flash v2.5 and $80 on Multilingual v2 (list prices read on October 20, 2026). Every provider charges less as the volume grows. The prices per character are converted at the 45,000 characters an hour Gradium publishes for its own voices. The [voice AI blog](/blog) ranks more providers on measured latency and price.

## Your own

Any other service plugs in by extending the [`TTS` class](/docs/text-to-speech/custom), and [`FallbackTTS`](/docs/text-to-speech/fallback) switches to another provider when one fails.
