[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Qwen Audio 3.0 TTS Flash](https://spiral.ai/integrations/opencode/qwen-audio-3-0-tts-flash)

# How to Use Qwen Audio 3.0 TTS Flash in opencode

Qwen Audio 3.0 TTS Flash turns written scripts into multilingual speech for spoken replies, explainers, and announcements. Compared with Qwen Audio 3.0 TTS Plus, it prioritizes fast speech generation over detailed vocal expression.

|  |  |
| --- | --- |
| Model | Qwen Audio 3.0 TTS Flash |
| Available through | fal |
| Category | Audio |
| Price | Each item in `text` adds $0.065. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen Audio 3.0 TTS Flash in opencode

- Read the project's onboarding guide and draft an English narration under 80 words. Use Qwen Audio 3.0 TTS Flash with Cherry and English selected, and save the script beside the generated audio.
- Turn the latest changelog entry into a spoken English release summary under 100 words. Preserve feature names, use Qwen Audio 3.0 TTS Flash with Serena, and save both the script and audio.
- Find the project's English and Spanish welcome messages. Generate a separate clip for each with Qwen Audio 3.0 TTS Flash, using Cherry and explicitly selecting the matching language.
- Use the project's password reset help text to draft a spoken explanation under 60 words. Generate it with Qwen Audio 3.0 TTS Flash, Cherry, and English selected.
- Write two short English readings of the project's welcome message, one beginning with [serious] and one with [excited]. Generate separate clips with Qwen Audio 3.0 TTS Flash using Cherry, and keep the scripts for comparison.

## How to set up Qwen Audio 3.0 TTS Flash in opencode

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Qwen Audio 3.0 TTS Flash**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "alibaba/qwen-audio-3-tts",
    "input": {
      "text": "Hello! This is Qwen Audio 3.0 speaking on fal."
    }
  }'
```

Then paste one of the prompts above: opencode finds Qwen Audio 3.0 TTS Flash on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/opencode

## Qwen Audio 3.0 TTS Flash tools and prices

- [Qwen Audio 3.0 TTS (Flash)](https://spiral.ai/tools/fal/alibaba/qwen-audio-3-tts) (fal): $0.065 per 1,000 characters of `text`. Rounded up to the next 1,000 characters, minimum 1,000.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| voice | Cherry, Serena, Ethan, Chelsie, Momo, Vivian, Moon, Maia, Kai, Nofish, Bella, Jennifer, Ryan, Katerina, Aiden, Mia, Mochi, Bellona, Vincent, Bunny, Neil, Elias, Arthur, Nini, Seren, Pip, Stella, Bodega, Sonrisa, Alek, Dolce, Sohee, Lenn, Emilien, Andre, Jada, Dylan, Li, Marcus, Roy, Peter, Sunny, Eric, Rocky, Kiki | Cherry | The voice used for speech synthesis. See the [Qwen-TTS voice list](https://www.alibabacloud.com/help/en/model-studio/qwen-tts-voice-list) for each voice's language and dialect coverage. |
| language | Auto, Chinese, English, Spanish, Russian, Italian, French, Korean, Japanese, German, Portuguese | Auto | Language of the input text. `Auto` lets the model detect it; setting it explicitly improves pronunciation and intonation. |

## What can you do with Qwen Audio 3.0 TTS Flash in opencode?

Add spoken walkthroughs, help messages, and release summaries to your project with Qwen Audio 3.0 TTS Flash. A coding agent can turn project text into short narration scripts and generate clips for review.

### Product walkthrough narration

Turn a short walkthrough script into spoken instructions. Generate one passage per task so you can review and replace individual sections.

### Spoken customer support replies

Convert an approved support answer into speech for order updates, appointment information, or common product questions.

### Multilingual announcements

Create spoken announcements from separately reviewed translations. Match each script's language to a compatible voice.

### Daily audio briefings

Turn a concise daily summary into a spoken briefing. Keep each passage focused on a few facts listeners need to remember.

### Short lesson narration

Convert a prepared explanation into speech for a short lesson. Produce separate clips for the explanation, example, and recap.

### Expressive dialogue drafts

Audition short scripted lines with emotion tags. Compare serious and excited readings before choosing a delivery.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## Qwen Audio 3.0 TTS Flash in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen-audio-3-0-tts-flash)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen-audio-3-0-tts-flash)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen-audio-3-0-tts-flash)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen-audio-3-0-tts-flash)
- [Cline](https://spiral.ai/integrations/cline/qwen-audio-3-0-tts-flash)
- [Codex](https://spiral.ai/integrations/codex/qwen-audio-3-0-tts-flash)
- [Cursor](https://spiral.ai/integrations/cursor/qwen-audio-3-0-tts-flash)
- [Devin](https://spiral.ai/integrations/devin/qwen-audio-3-0-tts-flash)
- [dots](https://spiral.ai/integrations/dots/qwen-audio-3-0-tts-flash)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen-audio-3-0-tts-flash)
- [Gemini](https://spiral.ai/integrations/gemini/qwen-audio-3-0-tts-flash)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen-audio-3-0-tts-flash)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen-audio-3-0-tts-flash)
- [goose](https://spiral.ai/integrations/goose/qwen-audio-3-0-tts-flash)
- [Grok](https://spiral.ai/integrations/grok/qwen-audio-3-0-tts-flash)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen-audio-3-0-tts-flash)
- [Hermes](https://spiral.ai/integrations/hermes/qwen-audio-3-0-tts-flash)
- [Instinct](https://spiral.ai/integrations/instinct/qwen-audio-3-0-tts-flash)
- [Manus](https://spiral.ai/integrations/manus/qwen-audio-3-0-tts-flash)
- [Muse](https://spiral.ai/integrations/muse/qwen-audio-3-0-tts-flash)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen-audio-3-0-tts-flash)
- [n8n](https://spiral.ai/integrations/n8n/qwen-audio-3-0-tts-flash)
- [Notion](https://spiral.ai/integrations/notion/qwen-audio-3-0-tts-flash)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen-audio-3-0-tts-flash)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen-audio-3-0-tts-flash)
- [Raycast](https://spiral.ai/integrations/raycast/qwen-audio-3-0-tts-flash)
- [VS Code](https://spiral.ai/integrations/vscode/qwen-audio-3-0-tts-flash)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen-audio-3-0-tts-flash)
- [Zapier](https://spiral.ai/integrations/zapier/qwen-audio-3-0-tts-flash)

## More opencode guides

- [Orpheus TTS](https://spiral.ai/integrations/opencode/orpheus-tts)
- [Qwen3 TTS 0.6B](https://spiral.ai/integrations/opencode/qwen3-tts-0-6b)
- [Nova-3 Multilingual](https://spiral.ai/integrations/opencode/nova-3-multilingual)
- [Qwen3 TTS 1.7B Clone Voice](https://spiral.ai/integrations/opencode/qwen3-tts-1-7b-clone-voice)
- [Nova-3](https://spiral.ai/integrations/opencode/nova-3)
- [Qwen3-TTS 0.6B Clone Voice](https://spiral.ai/integrations/opencode/qwen3-tts-0-6b-clone-voice)

## Questions about Qwen Audio 3.0 TTS Flash in opencode

**Can opencode use Qwen Audio 3.0 TTS Flash?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Qwen Audio 3.0 TTS Flash like any built-in tool.

**How much does Qwen Audio 3.0 TTS Flash cost in opencode?**

Each item in `text` adds $0.065. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

**Do I need a fal account to use Qwen Audio 3.0 TTS Flash in opencode?**

No. Spiral runs Qwen Audio 3.0 TTS Flash on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Qwen Audio 3.0 TTS Flash in opencode?**

About two minutes: add the server, then sign in, then check it.

**Does opencode wait while Qwen Audio 3.0 TTS Flash runs?**

Qwen Audio 3.0 TTS Flash runs in the background. opencode starts the run, checks on it and gives you the audio when it's ready.

**How does Qwen Audio 3.0 TTS Flash differ from Plus?**

Flash prioritizes fast speech generation for spoken interactions and customer service. Plus emphasizes synthesis quality and detailed vocal expression.

**How long can Qwen Audio 3.0 TTS speak?**

The maker reports up to three minutes of speech in one pass. Treat that as a reported capability rather than a guaranteed endpoint limit; split longer material into separate passages.

**What audio does Qwen Audio 3.0 TTS Flash produce?**

The endpoint's published example is a mono WAV file at 24 kHz. Check the returned file's metadata before preparing it for playback or editing.

**How can I improve pronunciation?**

Select the language that matches the script. The endpoint documentation says this improves pronunciation and intonation compared with automatic detection.

**Can Qwen Audio 3.0 TTS change emotion during a script?**

Yes. The maker demonstrates placing [serious] and [excited] directly before the relevant passages to change their delivery.

