[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Qwen3 TTS 1.7B Clone Voice](https://spiral.ai/integrations/opencode/qwen3-tts-1-7b-clone-voice)

# How to Use Qwen3 TTS 1.7B Clone Voice in opencode

Qwen3 TTS 1.7B Clone Voice turns a voice recording into a reusable speaker embedding for later speech generation. Unlike Qwen3 TTS 1.7B VoiceDesign, it starts from recorded speech rather than a written voice description.

|  |  |
| --- | --- |
| Model | Qwen3 TTS 1.7B Clone Voice |
| Available through | fal |
| Category | Audio |
| Price | Up to $0.00104 per run at the default inputs for 60 seconds of input. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen3 TTS 1.7B Clone Voice in opencode

- Use Qwen3 TTS 1.7B Clone Voice on the instructor recording in this project's narration assets. Include its exact transcript and save the returned embedding for the tutorial narrator.
- Prepare the onboarding presenter's voice with Qwen3 TTS 1.7B Clone Voice using the project's clean reference recording. Keep the returned embedding separate from playable audio assets.
- Use Qwen3 TTS 1.7B Clone Voice to extract an embedding from the character actor's reference recording in this project. Save it under the character's name for later dialogue synthesis.
- Check that the project's narrator reference is no longer than five minutes, then process it with Qwen3 TTS 1.7B Clone Voice. Preserve the exact transcript beside the returned voice asset.
- Use Qwen3 TTS 1.7B Clone Voice on the product demo narrator's recording. Save the embedding with the English and Spanish narration scripts for the later speech-generation stage.

## How to set up Qwen3 TTS 1.7B Clone Voice 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 Qwen3 TTS 1.7B Clone Voice**: 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": "fal-ai/qwen-3-tts/clone-voice/1.7b",
    "input": {
      "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/qwen3-tts/clone_in.mp3"
    }
  }'
```

Then paste one of the prompts above: opencode finds Qwen3 TTS 1.7B Clone Voice on Spiral, shows the price and runs it.

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

## Qwen3 TTS 1.7B Clone Voice tools and prices

- [Qwen 3 TTS 1.7B · Clone-Voice](https://spiral.ai/tools/fal/fal-ai/qwen-3-tts/clone-voice/1.7b) (fal): $0.00104 per minute.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| reference_text |  | — | Optional reference text that was used when creating the speaker embedding. Providing this can improve synthesis quality when using a cloned voice. |

## What can you do with Qwen3 TTS 1.7B Clone Voice in opencode?

Prepare reusable narrator voices for tutorials, onboarding, and game dialogue from recorded speech. A coding agent can organize the returned embeddings alongside the project's narration assets for a later text-to-speech step.

### Tutorial narrator preparation

Extract a speaker embedding from an instructor's recording for later tutorial narration.

### Multilingual narration preparation

Prepare a recorded narrator's voice for later speech generation in Qwen3 TTS's supported languages.

### Product onboarding voice

Create a reusable voice asset from a presenter's recording for spoken onboarding instructions.

### Training course voice assets

Prepare speaker embeddings from trainers' recordings for later lesson narration.

### Game character voice preparation

Extract a voice asset from an actor's character recording for later dialogue synthesis.

### Podcast announcement voice

Prepare a host's recorded voice for later synthesis of episode introductions and announcements.

### Recurring briefing narrator

Create a reusable speaker embedding for the text-to-speech stage of a recurring audio briefing.

## Overview

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

## Qwen3 TTS 1.7B Clone Voice in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen3-tts-1-7b-clone-voice)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen3-tts-1-7b-clone-voice)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen3-tts-1-7b-clone-voice)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen3-tts-1-7b-clone-voice)
- [Cline](https://spiral.ai/integrations/cline/qwen3-tts-1-7b-clone-voice)
- [Codex](https://spiral.ai/integrations/codex/qwen3-tts-1-7b-clone-voice)
- [Cursor](https://spiral.ai/integrations/cursor/qwen3-tts-1-7b-clone-voice)
- [Devin](https://spiral.ai/integrations/devin/qwen3-tts-1-7b-clone-voice)
- [dots](https://spiral.ai/integrations/dots/qwen3-tts-1-7b-clone-voice)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen3-tts-1-7b-clone-voice)
- [Gemini](https://spiral.ai/integrations/gemini/qwen3-tts-1-7b-clone-voice)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen3-tts-1-7b-clone-voice)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen3-tts-1-7b-clone-voice)
- [goose](https://spiral.ai/integrations/goose/qwen3-tts-1-7b-clone-voice)
- [Grok](https://spiral.ai/integrations/grok/qwen3-tts-1-7b-clone-voice)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen3-tts-1-7b-clone-voice)
- [Hermes](https://spiral.ai/integrations/hermes/qwen3-tts-1-7b-clone-voice)
- [Instinct](https://spiral.ai/integrations/instinct/qwen3-tts-1-7b-clone-voice)
- [Manus](https://spiral.ai/integrations/manus/qwen3-tts-1-7b-clone-voice)
- [Muse](https://spiral.ai/integrations/muse/qwen3-tts-1-7b-clone-voice)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen3-tts-1-7b-clone-voice)
- [n8n](https://spiral.ai/integrations/n8n/qwen3-tts-1-7b-clone-voice)
- [Notion](https://spiral.ai/integrations/notion/qwen3-tts-1-7b-clone-voice)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen3-tts-1-7b-clone-voice)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen3-tts-1-7b-clone-voice)
- [Raycast](https://spiral.ai/integrations/raycast/qwen3-tts-1-7b-clone-voice)
- [VS Code](https://spiral.ai/integrations/vscode/qwen3-tts-1-7b-clone-voice)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen3-tts-1-7b-clone-voice)
- [Zapier](https://spiral.ai/integrations/zapier/qwen3-tts-1-7b-clone-voice)

## More opencode guides

- [Qwen3 TTS 0.6B](https://spiral.ai/integrations/opencode/qwen3-tts-0-6b)
- [Qwen3-TTS 0.6B Clone Voice](https://spiral.ai/integrations/opencode/qwen3-tts-0-6b-clone-voice)
- [Qwen Audio 3.0 TTS Flash](https://spiral.ai/integrations/opencode/qwen-audio-3-0-tts-flash)
- [Qwen3-TTS 1.7B](https://spiral.ai/integrations/opencode/qwen3-tts-1-7b)
- [Orpheus TTS](https://spiral.ai/integrations/opencode/orpheus-tts)
- [Qwen3-TTS 1.7B Voice Design](https://spiral.ai/integrations/opencode/qwen3-tts-1-7b-voice-design)

## Questions about Qwen3 TTS 1.7B Clone Voice in opencode

**Can opencode use Qwen3 TTS 1.7B Clone Voice?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Qwen3 TTS 1.7B Clone Voice like any built-in tool.

**How much does Qwen3 TTS 1.7B Clone Voice cost in opencode?**

Up to $0.00104 per run at the default inputs for 60 seconds of input. 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 Qwen3 TTS 1.7B Clone Voice in opencode?**

No. Spiral runs Qwen3 TTS 1.7B Clone Voice on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Qwen3 TTS 1.7B Clone Voice in opencode?**

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

**Does opencode wait while Qwen3 TTS 1.7B Clone Voice runs?**

Qwen3 TTS 1.7B Clone Voice runs in the background. opencode starts the run, checks on it and gives you the audio when it's ready.

**Does Qwen3 TTS Clone Voice return speech I can play?**

It returns a speaker embedding in safetensors format. Creating spoken narration requires a separate text-to-speech step that uses that embedding.

**How much reference audio does Qwen3 TTS Clone Voice need?**

Qwen reports cloning from three seconds of speech. Use a short, clean recording and keep it within the five-minute input limit.

**What should I put in the reference transcript?**

Write exactly what the speaker says in the recording. Qwen's demo warns that cloning without reference text uses a lower-quality mode.

**Which languages does Qwen3 TTS support?**

Qwen documents speech generation in English, Chinese, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian. Language selection belongs to the later speech-generation step; cloning produces the speaker embedding.

**Can I create a voice by describing how it should sound?**

Qwen3 TTS Clone Voice starts from recorded speech. Qwen3 TTS VoiceDesign is the model for creating a voice from a written description.

