CosyVoice

CosyVoice

Alibaba
+
+

Related Products

  • Google Cloud Speech-to-Text
    366 Ratings
    Visit Website
  • Google AI Studio
    30 Ratings
    Visit Website
  • LALAL.AI
    5,230 Ratings
    Visit Website
  • DialerAI
    5 Ratings
    Visit Website
  • Adobe Firefly
    25,029 Ratings
    Visit Website
  • UptimeRobot
    840 Ratings
    Visit Website
  • TelemetryTV
    279 Ratings
    Visit Website
  • Community Phone
    1,404 Ratings
    Visit Website
  • QEval
    30 Ratings
    Visit Website
  • Datagate Telecom Billing
    12 Ratings
    Visit Website

About

Async is a developer-first AI voice platform, rooted in technology that powers Podcastle, offering premium text-to-speech and voice cloning via a simple, high-performance API. Developers gain access to broadcast-quality, natural-sounding voices with under-200 ms latency, and can create personalized voice clones using just a three-second audio sample. It supports streaming output so audio plays as it’s generated, and offers transparent usage-based billing with real-time daily stats and per-second cost control. Built to scale from prototypes to full production, Async makes advanced voice capabilities accessible to indie developers and enterprises alike, backed by the same trusted infrastructure that fueled Podcastle.

About

CosyVoice is Qwen Cloud’s voice cloning and speech synthesis model in the CosyVoice series, designed for professional text-to-speech scenarios with improved sound quality, naturalness, expressiveness, and cloning fidelity. With a short reference recording, it can create a highly similar custom voice without model training; Qwen recommends 10–20 seconds of clear speech, while at least five seconds of continuous speech is required. The model supports real-time, streaming text-to-speech synthesis, allowing applications to accept text and return audio with low first-packet latency. It supports Chinese, English, French, German, Japanese, Korean, and Russian for cloned voices, with language hints available to improve identification during enrollment. Source recordings can use WAV, MP3, or M4A formats and should contain clean speech without background music, noise, or additional speakers.

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Platforms Supported

Windows
Mac
Linux
Cloud
On-Premises
iPhone
iPad
Android
Chromebook

Audience

Developers wanting a tool to get natural voice generation and cloning for apps

Audience

Audiobook localization teams that need to clone voices and generate natural multilingual narration at scale

Support

Phone Support
24/7 Live Support
Online

Support

Phone Support
24/7 Live Support
Online

API

Offers API

API

Offers API

Screenshots and Videos

Screenshots and Videos

Pricing

$1 per hour
Free Version
Free Trial

Pricing

$0.26 per 10,000 characters
Free Version
Free Trial

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Reviews/Ratings

Overall 0.0 / 5
ease 0.0 / 5
features 0.0 / 5
design 0.0 / 5
support 0.0 / 5

This software hasn't been reviewed yet. Be the first to provide a review:

Review this Software

Training

Documentation
Webinars
Live Online
In Person

Training

Documentation
Webinars
Live Online
In Person

Company Information

Async
United States
async.ai/

Company Information

Alibaba
Founded: 1999
China
www.qwencloud.com/models/cosyvoice-v3-plus

Alternatives

Alternatives

Qwen3-TTS

Qwen3-TTS

Alibaba
Fish Audio

Fish Audio

Hanabi AI
Chirp 3

Chirp 3

Google
Fish Audio

Fish Audio

Hanabi AI

Categories

Categories

Integrations

JavaScript
Podcastle
Python
Qwen
Qwen Studio
QwenCloud
Twilio

Integrations

JavaScript
Podcastle
Python
Qwen
Qwen Studio
QwenCloud
Twilio
Claim Async and update features and information
Claim Async and update features and information
Claim CosyVoice and update features and information
Claim CosyVoice and update features and information